--- author: "Umesh Malik" canonical: "https://umesh-malik.com/blog" description: "Articles on Claude Code, AI coding agents, LLM engineering, RAG, OpenAI, Anthropic, and developer tooling. Written by Umesh Malik, software engineer and AI builder." title: "Blog — Claude Code, AI, LLMs & Developer Tooling | Umesh Malik" tokens: 21805 generator: "scripts/generate-page-markdown.mjs" --- # Blog Deep dives into AI engineering, GenAI applications, LLMs, and modern software development. Practical tutorials on RAG, agentic workflows, and building intelligent systems. Search Articles 121 matches Jump into Browse 121 articles across AI, frontend, performance, testing, and systems design. ## Topic Hubs [ Claude Code Guides on Anthropic's AI coding agent — account management, code review automation, and the latest Claude developments. ](https://umesh-malik.com/topics/claude-code)[ LLM Engineering RAG vs fine-tuning tradeoffs, running local LLMs, and deploying production language models with OpenAI and DeepSeek. ](https://umesh-malik.com/topics/llm-engineering)[ AI Coding Agents Agentic workflows, AGENTS.md, enterprise security, and the tools shaping autonomous software development. ](https://umesh-malik.com/topics/ai-coding-agents)[ MCP Build, deploy, and authenticate Model Context Protocol servers — typed tools agents can call instead of scraping HTML. ](https://umesh-malik.com/topics/mcp)[ AI Search & GEO Get cited in Google AI Overviews, AI Mode, ChatGPT, and Perplexity — GEO, llms.txt, and what still works in classic Search. ](https://umesh-malik.com/topics/ai-search)[ Claude Account Management Switch Claude Code accounts, work around rate limits, and run multiple Anthropic logins on one machine — without the browser OAuth dance. ](https://umesh-malik.com/topics/claude-account-management) ## Categories [Web Engineering (30)](https://umesh-malik.com/blog/category/web-engineering)[AI Coding Agents & DX (24)](https://umesh-malik.com/blog/category/ai-coding-agents-dx)[LLM Engineering (22)](https://umesh-malik.com/blog/category/llm-engineering)[AI Engineering (22)](https://umesh-malik.com/blog/category/ai-engineering)[AI Security (20)](https://umesh-malik.com/blog/category/ai-security)[Career & Productivity (3)](https://umesh-malik.com/blog/category/career-productivity) ## Featured Articles [![How to increase SEO traffic in the AI era — a hands-on field guide of genuine, repeatable techniques to earn clicks and AI citations in 2026](https://umesh-malik.com/blog/increase-seo-traffic-ai-era-techniques-cover.png) Web Engineering • Jul 29, 2026 ### How to Increase SEO Traffic in the AI Era: 10 Techniques (2026) How to increase SEO traffic in the AI era: 10 genuine, white-hat techniques anyone can use to earn clicks and citations from ChatGPT, Perplexity and AI Mode. 7 min read Read more →](https://umesh-malik.com/blog/increase-seo-traffic-ai-era-techniques) [![SEO in the AI era — the shift from ranking blue links to being cited inside AI-generated answers on ChatGPT, Perplexity and Google AI Mode](https://umesh-malik.com/blog/seo-in-the-ai-era-geo-playbook-cover.png) Web Engineering • Jul 27, 2026 ### SEO in the AI Era: The 2026 GEO Playbook for Winning AI Search Traffic SEO in the AI era: what actually changed, why clicks fell 60%, and the GEO playbook to earn traffic from ChatGPT, Perplexity and Google AI Mode in 2026. 11 min read Read more →](https://umesh-malik.com/blog/seo-in-the-ai-era-geo-playbook) [![Cover for the Claude Opus 5 guide: benchmarks, the $5/$25 cost math, effort levels, and the two API breaking changes in the Opus 4.8 migration](https://umesh-malik.com/blog/claude-opus-5-guide-cover.png) LLM Engineering • Jul 24, 2026 ### Claude Opus 5 Migration: The Two API Changes That Break Your Code Two API changes break a Claude Opus 5 migration, and the effort parameter needs re-sweeping, not reusing. The fixes, the real cost math, and the benchmarks. 12 min read Read more →](https://umesh-malik.com/blog/claude-opus-5-guide) ## Latest Articles [![Dashboard-style cover for reducing a Rust struct's memory footprint, showing five layout techniques and a 953-to-420-byte result](https://umesh-malik.com/blog/reduce-rust-struct-memory-footprint-cover.png) Web Engineering • Sep 4, 2026 ### How to Reduce Rust Struct Memory Footprint: 5 Techniques, 56% Smaller How to reduce Rust struct memory footprint: the 5 layout changes that shrank a real cache entry from 953 to 420 bytes, and what each one costs. 10 min read Read more →](https://umesh-malik.com/blog/reduce-rust-struct-memory-footprint) [![Migration flowchart showing OpenAI Python SDK moving from httpx with certifi to httpx2 with OS trust store](https://umesh-malik.com/blog/openai-python-httpx2-migration-guide-cover.png) LLM Engineering • Aug 29, 2026 ### OpenAI Python HTTPX2 Migration: Fix the TLS Trap First The OpenAI Python HTTPX2 migration breaks certifi TLS in containers and proxies. The full checklist, OS trust store fix, and legacy escape hatch. 6 min read Read more →](https://umesh-malik.com/blog/openai-python-httpx2-migration-guide) [![Cover showing the PCIe bottleneck in traditional GPU-NIC architecture versus MTIA 300's built-in NIC design that delivers 1.2 TB/s without CPU mediation](https://umesh-malik.com/blog/eliminate-pcie-bottleneck-ai-training-cover.png) AI Engineering • Aug 25, 2026 ### Fix the PCIe Bottleneck in AI Training: How Built-in NICs Work Fix the PCIe bottleneck in AI training with built-in NICs. Meta's MTIA 300 reclaims 1.2 TB/s by eliminating host CPU mediation. 9 min read Read more →](https://umesh-malik.com/blog/eliminate-pcie-bottleneck-ai-training) [![The flow from prompt to invisible watermark: Paint sends a prompt to Microsoft's moderation server, receives a GUID, runs local inference, then embeds that GUID into the pixels](https://umesh-malik.com/blog/ms-paint-invisible-watermark-guid-cover.png) AI Security • Aug 25, 2026 ### MS Paint Invisible Watermark: How to Find the GUID in AI Images The MS Paint invisible watermark embeds a server GUID into every AI image — even when inference runs locally. Here's how to detect it. 8 min read Read more →](https://umesh-malik.com/blog/ms-paint-invisible-watermark-guid) [![Cover showing the inference engine attack surface with token stream flowing from model through vulnerable parser to arbitrary code execution, and the defense architecture separating GPU host from token parsing](https://umesh-malik.com/blog/secure-llm-inference-vllm-cve-2025-9141-cover.png) AI Security • Aug 25, 2026 ### How to Harden vLLM Inference: CVE-2025-9141 Defense Guide How to harden vLLM inference against token exploits. CVE-2025-9141 let models run code via eval(). Separate GPU hosts from parsers. 9 min read Read more →](https://umesh-malik.com/blog/secure-llm-inference-vllm-cve-2025-9141) [![Chart showing ChatGPT Search site-scoped query share jumping from 0.3% to 17% on August 8, 2026](https://umesh-malik.com/blog/chatgpt-search-site-scoping-geo-cover.png) LLM Engineering • Aug 24, 2026 ### ChatGPT Search Optimization After the Site-Scoping Shift ChatGPT search optimization changed when 17% of queries started scoping to specific sites. What the GPT-5.6 shift means and how to get cited. 7 min read Read more →](https://umesh-malik.com/blog/chatgpt-search-site-scoping-geo) [![Diagram showing robots.txt preferences syncing with Cloudflare's AI bot enforcement rules across Search, Agent, and Training categories](https://umesh-malik.com/blog/sync-robots-txt-ai-bot-blocks-cover.png) AI Security • Aug 24, 2026 ### How to Block AI Training Without Losing Search Visibility Block AI training without losing search by setting one toggle. Bot Preference Sync writes robots.txt from your dashboard — no static file to maintain. 8 min read Read more →](https://umesh-malik.com/blog/sync-robots-txt-ai-bot-blocks) [![OAuth consent screen with optional scope checkboxes that let users narrow agent permissions](https://umesh-malik.com/blog/optional-oauth-scopes-mcp-servers-cover.png) Web Engineering • Aug 23, 2026 ### Configure Optional OAuth Scopes for MCP Servers and Agents Configure optional OAuth scopes so users can narrow agent permissions at consent. The API call, the UX, and handling partial grants. 6 min read Read more →](https://umesh-malik.com/blog/optional-oauth-scopes-mcp-servers) [![Memory comparison between rust-analyzer and Rust Glancer showing the dramatic reduction from gigabytes to under 100MB](https://umesh-malik.com/blog/rust-glancer-low-memory-lsp-cover.png) AI Coding Agents & DX • Aug 23, 2026 ### Rust LSP Low Memory: How to Run Glancer Locally on 8GB RAM Rust LSP low memory is achievable: Rust Glancer runs on 8GB machines by freezing analysis at save and offloading to disk. 8 min read Read more →](https://umesh-malik.com/blog/rust-glancer-low-memory-lsp) [![Architecture diagram of a self-hosted AI coding agent with sandboxed execution](https://umesh-malik.com/blog/self-hosted-ai-coding-agent-sandbox-cover.png) AI Coding Agents & DX • Aug 23, 2026 ### Self-Hosted AI Coding Agent: Sandboxed Prompt-to-Deploy for $25/mo Build a self-hosted AI coding agent with sandboxed execution. One prompt produces a repo, tests, CI, and deployed app — $25/mo, no cloud bills. 7 min read Read more →](https://umesh-malik.com/blog/self-hosted-ai-coding-agent-sandbox) [![Vercel CLI DNS management workflow showing terminal commands for DNS records, domains, and project control](https://umesh-malik.com/blog/vercel-cli-dns-commands-cover.png) Web Engineering • Aug 23, 2026 ### Vercel CLI DNS Commands: Manage Records Without the Dashboard Use Vercel CLI DNS commands to manage records, renew domains, and pause projects from terminal. Automate with --json output. 6 min read Read more →](https://umesh-malik.com/blog/vercel-cli-dns-commands) [![The four-step path from HP's unsupported printer to a native macOS driver: Docker workaround, byte-diff against an open-source filter, the DPI bug isolated, then a native USB backend](https://umesh-malik.com/blog/claude-code-macos-printer-driver-cover.png) AI Coding Agents & DX • Aug 19, 2026 ### Claude Code macOS printer driver: fixing the DPI bug HP missed A Claude Code macOS printer driver project fixed a printer HP never supported — by diffing raw output byte-by-byte until a silent DPI mismatch turned up. 10 min read Read more →](https://umesh-malik.com/blog/claude-code-macos-printer-driver) [![The five sandbox tools a Gemini agent hook intercepts, against the two tool families it never sees](https://umesh-malik.com/blog/gemini-agent-hooks-fail-open-cover.png) AI Security • Aug 19, 2026 ### Gemini agent hooks fail open: how to block a tool call anyway Gemini agent hooks fail open on every error path, and never fire for MCP or function tools. The deny contract, the coverage gap, and what to gate instead. 9 min read Read more →](https://umesh-malik.com/blog/gemini-agent-hooks-fail-open) [![Rust GPU offload safety and performance: ownership rules managing host-device transfers, benchmarked against hand-tuned CUDA and HIP](https://umesh-malik.com/blog/rust-safe-gpu-offload-benchmarks-cover.png) AI Engineering • Aug 19, 2026 ### Rust GPU Offload Without unsafe: The 400x Mistake That Isn't Safety Rust GPU offload now works without unsafe code. Real benchmarks: 11% faster to 46% slower than CUDA on an H100, and a transfer bug that costs 400x more. 8 min read Read more →](https://umesh-malik.com/blog/rust-safe-gpu-offload-benchmarks) [![A browser tab converting an animated SVG into an MP4 video entirely client-side using a 30MB ffmpeg.wasm build, with no server round trip](https://umesh-malik.com/blog/svg-to-mp4-in-the-browser-cover.png) Web Engineering • Aug 19, 2026 ### SVG to MP4 in the browser: a two-step workflow, no server SVG to MP4 in the browser needs no server: paste a URL and 30MB of ffmpeg.wasm renders every frame in your tab. The one catch that trips people up. 8 min read Read more →](https://umesh-malik.com/blog/svg-to-mp4-in-the-browser) [![Cover graphic showing the four-step baseline method — 5-minute buckets, 3-week median, independent-cause match, verdict — next to the eclipse's 15-30% traffic-drop metrics](https://umesh-malik.com/blog/traffic-anomaly-or-outage-baseline-method-cover.png) Web Engineering • Aug 19, 2026 ### Traffic Anomaly or Outage? What a 30% Drop Actually Means A 15-30% traffic anomaly or outage? Cloudflare's eclipse analysis shows the fix: five-minute buckets against a three-week matched baseline. 7 min read Read more →](https://umesh-malik.com/blog/traffic-anomaly-or-outage-baseline-method) [![A map of five infrastructure components replaced by PostgreSQL features, each annotated with the threshold where the swap stops working](https://umesh-malik.com/blog/use-postgres-for-everything-cover.png) Web Engineering • Aug 19, 2026 ### Use Postgres for everything in production: 5 swaps, 1 cliff Use Postgres for everything and four of the five swaps hold. The queue is the one that death-spirals: 383,000 dead tuples and 300ms locks at 800 jobs/sec. 8 min read Read more →](https://umesh-malik.com/blog/use-postgres-for-everything) [![A claimed 1.4x speedup collapsing to 1.5x slower as the same code is checked against a holdout benchmark and then audited for interface cheating](https://umesh-malik.com/blog/verify-ai-agent-benchmark-claims-cover.png) AI Coding Agents & DX • Aug 19, 2026 ### How to verify AI-generated benchmark claims: 1.4x to 1.5x slower How to verify AI-generated benchmark claims: an LLM agent's regex engine beat Rust's regex crate by 1.4x on rebar, then lost 10x on a holdout it never saw. 9 min read Read more →](https://umesh-malik.com/blog/verify-ai-agent-benchmark-claims) [![The four layers at which an AI feature can be switched off, ranked by which events reset each one](https://umesh-malik.com/blog/turn-off-ai-features-permanently-cover.png) AI Security • Aug 18, 2026 ### Turn off AI features permanently: configure 1 policy, not 25 toggles Turn off AI features permanently with policy, not toggles: one Chrome default covers 25 gen-AI features, and Microsoft has deprecated the Copilot policy. 11 min read Read more →](https://umesh-malik.com/blog/turn-off-ai-features-permanently) [![An author's intent passing through a draft and an AI rewrite before reaching the reader, losing emphasis, certainty and priority at each hop](https://umesh-malik.com/blog/ai-writing-policy-for-engineers-cover.png) Career & Productivity • Aug 17, 2026 ### AI writing policy for engineers: the template and 5 checks An AI writing policy for engineers works only if it governs accountability, not tool use. The five-line template, the mechanism behind it, five review checks. 13 min read Read more →](https://umesh-malik.com/blog/ai-writing-policy-for-engineers) [![Cloudflare's edge injecting the beacon.min.js analytics script into an HTML response before it reaches the browser](https://umesh-malik.com/blog/remove-cloudflare-beacon-min-js-cover.png) Web Engineering • Aug 17, 2026 ### Remove Cloudflare beacon.min.js: you must opt in to opt out Remove Cloudflare beacon.min.js for good: the disable toggle hides behind adding your site to Web Analytics first, and no-transform is the stronger lever. 9 min read Read more →](https://umesh-malik.com/blog/remove-cloudflare-beacon-min-js) [![Two CPU pools under a sched\_ext policy: latency-critical request threads separated from background work, with a watchdog fallback to EEVDF](https://umesh-malik.com/blog/fix-eevdf-latency-regression-sched-ext-cover.png) Web Engineering • Aug 16, 2026 ### Fix EEVDF latency regressions with sched\_ext: Meta's 28% p99 win Your p99 got worse after a kernel upgrade and nothing else changed? That is an EEVDF latency regression. Meta cut p99 28% with a two-pool sched\_ext policy. 12 min read Read more →](https://umesh-malik.com/blog/fix-eevdf-latency-regression-sched-ext) [![Three brain-wiring strategies compared by information cost, from an infeasible 3x10^15 bits down to a genome-feasible 300 million bits](https://umesh-malik.com/blog/how-dna-wires-a-brain-cover.png) AI Engineering • Aug 16, 2026 ### How DNA wires a brain: 300M bits for 100 trillion connections How DNA wires a brain: a ~10B-bit genome must wire 100 trillion connections. The scheme that closes the gap in 300M bits, and why two simpler plans fail first. 9 min read Read more →](https://umesh-malik.com/blog/how-dna-wires-a-brain) [![The five feature-flagged phases of a zero-downtime datastore migration, from dual writes through shadow reads to cutover](https://umesh-malik.com/blog/zero-downtime-database-migration-dual-writes-cover.png) Web Engineering • Aug 16, 2026 ### Zero downtime database migration: 5 flags and a 17x P90 gap A zero downtime database migration is five feature-flagged phases, not a cutover. P95 said 4x slower, P90 said 17x, and the comparison code took a region down. 12 min read Read more →](https://umesh-malik.com/blog/zero-downtime-database-migration-dual-writes) [![Cloudflare Access enforcing an identity policy in front of a Worker before its code executes](https://umesh-malik.com/blog/cloudflare-access-for-workers-cover.png) AI Security • Aug 15, 2026 ### Configure Cloudflare Access for Workers: auth before your code runs Cloudflare Access for Workers checks requests before your code runs — no JWT validation. The three scopes, the local-dev config, and what it still misses. 8 min read Read more →](https://umesh-malik.com/blog/cloudflare-access-for-workers) [![Qwen3.8 27B VRAM budget: FP8 weights plus KV cache at 262K context on a single GPU](https://umesh-malik.com/blog/qwen3-8-27b-vram-kv-cache-math-cover.png) LLM Engineering • Aug 15, 2026 ### Qwen3.8 27B VRAM: how to fit 262K context in 16 GiB, not 64 Qwen3.8 27B VRAM math: 25.9 GiB of FP8 weights plus 16 GiB of KV cache at 262,144 tokens, not 64. The arithmetic, and where a 48 GB card breaks. 9 min read Read more →](https://umesh-malik.com/blog/qwen3-8-27b-vram-kv-cache-math) [![Swapping bespoke search tools for generic grep, glob and view raised Copilot code review cost until the system prompt was rewritten to be diff-anchored](https://umesh-malik.com/blog/cut-agent-tool-call-cost-prompt-rewrite-cover.png) AI Coding Agents & DX • Aug 14, 2026 ### Cut agent tool call cost: GitHub's 20% fix was a prompt rewrite Agent tool call cost jumped after you gave it better tools? GitHub hit that on Copilot code review and won ~20% back with a prompt rewrite, not new tools. 9 min read Read more →](https://umesh-malik.com/blog/cut-agent-tool-call-cost-prompt-rewrite) [![The four integration seams a cloud provider fills for Kubernetes, and what you must build yourself on bare metal](https://umesh-malik.com/blog/kubernetes-on-bare-metal-cloud-integrations-cover.png) Web Engineering • Aug 14, 2026 ### Kubernetes on bare metal: the 4 cloud integrations you must build Run Kubernetes on bare metal and four integrations become yours: node identity, LoadBalancer IPs, provisioning, storage. Oxide shipped three; one is blocked. 10 min read Read more →](https://umesh-malik.com/blog/kubernetes-on-bare-metal-cloud-integrations) [![A research spike shipped as running code surfaces engine-specific blockers a design doc would have missed](https://umesh-malik.com/blog/research-spike-as-running-code-cover.png) AI Coding Agents & DX • Aug 13, 2026 ### Build your research spike as running code: 8 blockers a doc missed A research spike should ship as running code, not a design doc. alchemy-utils surfaced 8 engine blockers a doc would miss, and priced the fix at 3-5 weeks. 10 min read Read more →](https://umesh-malik.com/blog/research-spike-as-running-code) [![Verifying AI crawler identity by matching source IPs against published CIDR lists instead of trusting the User-Agent header](https://umesh-malik.com/blog/verify-ai-crawler-ips-not-user-agents-cover.png) AI Security • Aug 13, 2026 ### How to Verify AI Crawler IPs: 3 Lists Are Over a Year Stale Verify AI crawler IPs instead of trusting the User-Agent: the CIDR check for ClaudeBot and GPTBot, and the three published lists that are over a year stale. 8 min read Read more →](https://umesh-malik.com/blog/verify-ai-crawler-ips-not-user-agents) [![How server-side compaction replaces a long agent transcript with a single summary block once input tokens cross the trigger, and what is kept versus permanently dropped](https://umesh-malik.com/blog/agent-context-compaction-what-survives-cover.png) AI Engineering • Aug 12, 2026 ### Agent context compaction: keep what the 150K cutoff drops Agent context compaction drops every block before the summary at 150K tokens. What survives, what instructions silently replaces, and the usage field that lies. 9 min read Read more →](https://umesh-malik.com/blog/agent-context-compaction-what-survives) [![The metrics path behind WhatsApp Scam Alert, where device identity, IP address and per-user counters are each stripped at a different hop before any number reaches Meta](https://umesh-malik.com/blog/on-device-ai-without-breaking-e2ee-cover.png) AI Security • Aug 12, 2026 ### Build on-device AI without breaking E2EE: the metrics leak first Local inference is the easy half of on-device AI without breaking E2EE. The hard half is telemetry: two TEEs, k-anonymity, DP noise, and a ledger you don't own. 9 min read Read more →](https://umesh-malik.com/blog/on-device-ai-without-breaking-e2ee) [![How a paravirtualized Metal device reporting Apple GPU family 5 makes llama.cpp disable its simdgroup matrix kernels, and the throughput that returns when the guest reports family 9](https://umesh-malik.com/blog/fix-slow-llm-inference-macos-vms-cover.png) LLM Engineering • Aug 11, 2026 ### Fix slow LLM inference in macOS VMs: 12.6 → 207 tok/s LLM inference in macOS VMs collapses to 12.63 tok/s because the guest reports GPU family 5 and llama.cpp drops its matrix kernels. The check, and its limits. 9 min read Read more →](https://umesh-malik.com/blog/fix-slow-llm-inference-macos-vms) [![The four-step loop for learning a complex topic by having an AI coding agent build an interactive simulation of it](https://umesh-malik.com/blog/learn-complex-topics-claude-code-simulations-cover.png) AI Coding Agents & DX • Aug 11, 2026 ### Learn Complex Topics With Claude Code: Build a Simulation, Not Notes Learn complex topics with Claude Code by building a small simulation of the mechanism: the 4-step loop, the fact-check gate LLMs skip, and how to ship it free. 8 min read Read more →](https://umesh-malik.com/blog/learn-complex-topics-claude-code-simulations) [![Muse Glimmer 30B memory ladder showing 55GB at full precision shrinking to under 20GB with 4-bit K-Quant compression](https://umesh-malik.com/blog/run-muse-glimmer-30b-locally-cover.png) AI Coding Agents & DX • Aug 11, 2026 ### Run Muse Glimmer 30B locally: 55GB shrinks to under 20GB How to run Muse Glimmer 30B locally: the K-Quant setup that fits a single 24GB GPU, the drafter model that triples decode speed, and where it breaks. 8 min read Read more →](https://umesh-malik.com/blog/run-muse-glimmer-30b-locally) [![Timeline comparing the knowledge-cutoff date vendors claim for Claude Opus 5 against the earlier cutoff its answers actually reveal](https://umesh-malik.com/blog/testing-llm-knowledge-cutoffs-opus-5-cover.png) LLM Engineering • Aug 11, 2026 ### How to Test an LLM's Knowledge Cutoff: Opus 5's May Claim Falls Short Here's how to test an LLM's knowledge cutoff with three reproducible probes — the method showing Opus 5 claims May 2026 but answers like January 2026. 7 min read Read more →](https://umesh-malik.com/blog/testing-llm-knowledge-cutoffs-opus-5) [![Cover showing the four-layer agent containment stack — deny egress, scope identity, watch live, kill fast — alongside the AISI evaluation figures of 122 runs, 10 off-scope runs and containment in under an hour](https://umesh-malik.com/blog/sandbox-ai-agent-internet-access-cover.png) AI Security • Aug 8, 2026 ### How to sandbox an AI agent: 10 of 122 eval runs went rogue AISI logged 19 unsanctioned actions across 122 cyber-eval runs. How to sandbox an AI agent at the network layer — the control that blocks, not just detects. 10 min read Read more →](https://umesh-malik.com/blog/sandbox-ai-agent-internet-access) [![Cover showing the vLLM VRAM budget split into model weights, runtime overhead and KV cache, with the KV cache block math that converts free VRAM into concurrent sequences](https://umesh-malik.com/blog/vllm-throughput-tuning-flags-cover.png) LLM Engineering • Aug 8, 2026 ### vLLM throughput tuning: configure these four flags, not a bigger GPU vLLM throughput tuning starts with KV cache blocks, not a bigger GPU. The four flags that decide your tokens/sec, and the one that quietly backfires. 10 min read Read more →](https://umesh-malik.com/blog/vllm-throughput-tuning-flags) [![Cover card titled Approve, subtitled One in three gets through, with three statistics: 409,000 approve or deny decisions analysed, 66.3% mean accuracy, and 52.5% miss rate on npm-disguised exfiltration](https://umesh-malik.com/blog/ai-agent-permissions-approval-fatigue-cover.png) AI Security • Aug 7, 2026 ### Configuring AI Agent Permissions: Humans Miss 1 in 3 Threats 409,000 approve/deny decisions show humans miss 1 in 3 agent threats, and 52.5% of npm-shaped exfiltration. The AI agent permissions config that works instead. 10 min read Read more →](https://umesh-malik.com/blog/ai-agent-permissions-approval-fatigue) [![Diagram of a Workers AI request routed through AI Gateway, showing the payload log, token count and cost attribution captured at the gateway hop](https://umesh-malik.com/blog/ai-gateway-for-workers-ai-cover.png) AI Engineering • Aug 7, 2026 ### Set up AI Gateway for Workers AI: one argument, every call logged AI Gateway for Workers AI is now one argument on env.AI.run. What it logs instantly, why caching stays off until you ask, and the 60-second TTL floor. 10 min read Read more →](https://umesh-malik.com/blog/ai-gateway-for-workers-ai) [![Diagram of the Datasette filter injection — a query-string column name flows unquoted into generated SQL and returns rows from a private table](https://umesh-malik.com/blog/datasette-sql-injection-patch-cover.png) Web Engineering • Aug 7, 2026 ### Fix the Datasette SQL Injection: Why execute-sql Won't Save You The Datasette SQL injection patched in 1.0a38 and 0.65.3 leaks private tables via unescaped filter columns. The check, upgrade, and why execute-sql is no fix. 8 min read Read more →](https://umesh-malik.com/blog/datasette-sql-injection-patch) [![The four agentic web layers — readable, discoverable, callable, payable — mapped to concrete URLs on a static site](https://umesh-malik.com/blog/make-your-site-agent-readable-cover.png) Web Engineering • Aug 7, 2026 ### How to Make Your Site Agent-Readable: 4 Layers, One Worker Make your site agent-readable in four layers — readable, discoverable, callable, payable. Three are build-time files; only /mcp needs a Worker. 10 min read Read more →](https://umesh-malik.com/blog/make-your-site-agent-readable) [![The browsing loop a code-review agent enters under generic tool instructions, versus the diff-anchored evidence path review-shaped instructions produce](https://umesh-malik.com/blog/writing-agent-tool-instructions-cover.png) AI Coding Agents & DX • Aug 7, 2026 ### Fix your agent tool instructions: GitHub's 20% review-cost cut Agent tool instructions decide what your agent costs. GitHub kept the same grep/glob/view toolset, rewrote the guidance, and cut review cost by ~20%. 9 min read Read more →](https://umesh-malik.com/blog/writing-agent-tool-instructions) [![Ads for AI agents: TIME serves markdown with sponsored FAQ blocks to AI crawlers and HTML to humans](https://umesh-malik.com/blog/ads-for-ai-agents-time-markdown-crawlers-cover.png) AI Engineering • Aug 6, 2026 ### Ads for AI Agents: TIME Serves Crawlers a Different Site Ads for AI agents are live. TIME serves crawlers a 42 KB markdown site with sponsored blocks; humans and Googlebot get 1.2 MB of HTML. I measured all of it. 10 min read Read more →](https://umesh-malik.com/blog/ads-for-ai-agents-time-markdown-crawlers) [![Diagram of Dependabot running two independent lanes: version updates funnelled through cooldown and a monthly schedule into one grouped pull request, and security updates bypassing all of it to open immediately](https://umesh-malik.com/blog/dependabot-grouped-updates-cut-pr-noise-cover.png) Web Engineering • Aug 6, 2026 ### Configure Dependabot grouped updates: one PR a month, CVEs instant Dependabot grouped updates fold a month of version bumps into one pull request while CVE fixes still land same-day. The cooldown key most configs miss. 9 min read Read more →](https://umesh-malik.com/blog/dependabot-grouped-updates-cut-pr-noise) [![Diagram contrasting a sequential agent loop of ten model round trips with a two-level dependency graph running nine tool calls concurrently](https://umesh-malik.com/blog/parallel-agent-tool-calls-dag-harness-cover.png) AI Engineering • Aug 6, 2026 ### Run agent tool calls in parallel: 10 turns become 2 DAG levels Run agent tool calls in parallel by swapping the loop for a DAG planner: ten round trips become two levels, plus the cap, budget and critic on top. 10 min read Read more →](https://umesh-malik.com/blog/parallel-agent-tool-calls-dag-harness) [![Reinforcement fine-tuning: a 4B open model matching a frontier LLM on retrieval at a fraction of the cost](https://umesh-malik.com/blog/reinforcement-fine-tuning-small-models-retrieval-cover.png) LLM Engineering • Aug 6, 2026 ### Reinforcement Fine-Tuning: When a 4B Model Beats GPT-5.6 Reinforcement fine-tuning let a 4B open model match GPT-5.6 Sol on retrieval at 100x lower cost. How RFT works, and when it beats prompting a frontier LLM. 10 min read Read more →](https://umesh-malik.com/blog/reinforcement-fine-tuning-small-models-retrieval) [![Diagram of a CI pipeline expressed as a Cloudflare Workflow: one cached install step fanning out to four parallel checks and joining into a deploy step](https://umesh-malik.com/blog/run-cicd-cloudflare-workflows-cover.png) AI Coding Agents & DX • Aug 6, 2026 ### Run CI/CD on Cloudflare Workflows: deploy in 18 lines, 33 free runs Run CI/CD on Cloudflare Workflows and a GitHub Actions YAML becomes 18 lines of TypeScript. Which meter bills first, and what private beta still blocks. 10 min read Read more →](https://umesh-malik.com/blog/run-cicd-cloudflare-workflows) [![Rust LLM policy: AI allowed for review and analysis, banned for creating code and prose](https://umesh-malik.com/blog/rust-llm-policy-ai-generated-code-cover.png) AI Coding Agents & DX • Aug 6, 2026 ### Rust LLM Policy: Use AI to Review, Not to Create The Rust LLM policy bans AI-created code and prose but allows AI review, analysis, and bug-finding. Here's the exact rule, why it works, and how to copy it. 10 min read Read more →](https://umesh-malik.com/blog/rust-llm-policy-ai-generated-code) [![Agent harness design diagram: a model's reasoning discarded each turn versus reasoning retained and context compacted across turns](https://umesh-malik.com/blog/agent-harness-design-arc-agi-3-cover.png) AI Engineering • Aug 5, 2026 ### Agent Harness Design: Why an ARC-AGI-3 Score Tripled Agent harness design decided a benchmark: OpenAI's ARC-AGI-3 score went 13.3% → 38.3% with zero model changes. What that means for your agent loop. 11 min read Read more →](https://umesh-malik.com/blog/agent-harness-design-arc-agi-3) [![Cover card titled The Exit, subtitled Badge returned. Access still live., with three statistics: 2 named defendants in Apple Inc. v. Liu, 11 additional former employees named in the filing, and reasonable measures as the statutory test for a trade secret](https://umesh-malik.com/blog/insider-threat-offboarding-controls-cover.png) AI Security • Aug 5, 2026 ### Insider Threat Offboarding Controls: The Apple v. OpenAI Lesson Insider threat offboarding controls, read through Apple v. OpenAI: retained devices, live access, and why weak offboarding also weakens your legal claim. 11 min read Read more →](https://umesh-malik.com/blog/insider-threat-offboarding-controls) [![LLM abuse detection diagram contrasting per-message content classification with account-level behavioural correlation across a session corpus](https://umesh-malik.com/blog/llm-abuse-detection-openai-scam-network-cover.png) AI Security • Aug 5, 2026 ### LLM Abuse Detection: What OpenAI's Scam Ban Reveals LLM abuse detection failed at the message level and worked at the account level. OpenAI's Cambodia scam ban shows which signal actually catches misuse. 11 min read Read more →](https://umesh-malik.com/blog/llm-abuse-detection-openai-scam-network) [![MCP write controls diagram: a tool call passing through a policy layer that allows, labels, or blocks it before the handler runs](https://umesh-malik.com/blog/mcp-write-controls-cloudflare-writeguard-cover.png) AI Security • Aug 5, 2026 ### MCP Write Controls: Lessons from Cloudflare WriteGuard MCP write controls decide what your agents can break. Cloudflare's WriteGuard shows the pattern: per-tool risk tiers, agent attribution, central audit. 13 min read Read more →](https://umesh-malik.com/blog/mcp-write-controls-cloudflare-writeguard) [![Cover card titled The Gate, subtitled Thousands of tickets. One agent., with three statistics: 4 risk tiers, Cloudflare's MCP portal growing 13 to 27 servers, and tool annotations marked untrusted per the MCP spec](https://umesh-malik.com/blog/secure-mcp-write-tools-writeguard-cover.png) AI Security • Aug 5, 2026 ### How to Secure MCP Write Tools: Cloudflare's WriteGuard Lesson How to secure MCP write tools: the spec puts confirmation on the client — the one layer you don't control. Cloudflare's WriteGuard moves the gate server-side. 11 min read Read more →](https://umesh-malik.com/blog/secure-mcp-write-tools-writeguard) [![Diagram of an AI agent paying an API over the x402 HTTP 402 protocol using a Cloudflare Virtual Wallet](https://umesh-malik.com/blog/cloudflare-wallets-x402-agent-payments-cover.png) AI Engineering • Aug 4, 2026 ### Cloudflare Wallets and x402: How AI Agents Pay for APIs Cloudflare Wallets and x402 explained: how AI agents get a spending identity, how HTTP 402 payments work, and what breaks when your agent holds a budget. 10 min read Read more →](https://umesh-malik.com/blog/cloudflare-wallets-x402-agent-payments) [![A fabricated CVE advisory flowing unverified into the public vulnerability database pipeline](https://umesh-malik.com/blog/fake-cve-reports-ai-slop-sqlite-cover.png) AI Security • Aug 4, 2026 ### Fake CVE Reports: 54 of 55 SQLite Advisories Were AI Slop Fake CVE reports are now cheaper to write than to disprove. JFrog found 54 of 55 SQLite advisories fabricated by an LLM. How to spot them before you patch. 11 min read Read more →](https://umesh-malik.com/blog/fake-cve-reports-ai-slop-sqlite) [![Diagram of an LLM eval framework pipeline: tasks and configs produce runs, graders apply checks to produce grades](https://umesh-malik.com/blog/llm-eval-framework-smevals-cover.png) LLM Engineering • Aug 4, 2026 ### LLM Eval Framework: Grade Prompts, Models and Harnesses An LLM eval framework turns vibes into scores. How smevals structures tasks, configs, runners and graders — and how to ship your first eval today. 10 min read Read more →](https://umesh-malik.com/blog/llm-eval-framework-smevals) [![Production-grade AI agents — the funnel from 353,000 course registrations down to 6,000 shipped agent projects](https://umesh-malik.com/blog/production-grade-ai-agents-vibe-to-live-gap-cover.png) AI Engineering • Aug 4, 2026 ### Production-Grade AI Agents: The Vibe-to-Live Gap Production-grade AI agents need more than a working demo. 353,000 signed up to learn agents; 6,000 shipped a capstone. Here's exactly what closes the gap. 11 min read Read more →](https://umesh-malik.com/blog/production-grade-ai-agents-vibe-to-live-gap) [![Layer-by-layer LLM inference streaming one transformer layer at a time from disk onto a 4GB GPU](https://umesh-malik.com/blog/run-70b-llm-on-4gb-gpu-airllm-cover.png) LLM Engineering • Aug 4, 2026 ### Run 70B LLM on 4GB GPU: AirLLM's Real Tradeoff Run 70B LLM on 4GB GPU hardware with AirLLM's layer-by-layer inference. The VRAM math is real — you just pay for it in disk bandwidth. The honest tradeoff. 11 min read Read more →](https://umesh-malik.com/blog/run-70b-llm-on-4gb-gpu-airllm) [![Agent-to-human delegation — an AI agent handing a task to a human coworker in a chat tool](https://umesh-malik.com/blog/agent-to-human-delegation-cover.png) AI Engineering • Aug 3, 2026 ### Agent-to-Human Delegation: Why Your AI Shouldn't DM Coworkers Agent-to-human delegation is the pattern nobody designed for: your AI messaging a coworker. Why it lands badly, and the handoff rules that fix it. 10 min read Read more →](https://umesh-malik.com/blog/agent-to-human-delegation) [![Explorative modeling diagram: K candidate generations compared against real data, with only the closest match receiving gradients](https://umesh-malik.com/blog/explorative-modeling-train-on-best-of-k-cover.png) AI Engineering • Aug 2, 2026 ### Explorative Modeling: Train on the Best of K Guesses Explorative modeling factors the training loop instead of generation: sample K guesses, train only on the best. 4.1x FLOP efficiency, 1.43 FID on ImageNet. 8 min read Read more →](https://umesh-malik.com/blog/explorative-modeling-train-on-best-of-k) [![DeepSeek V4 Flash 0731 agent benchmark results compared against the preview build and V4-Pro Preview](https://umesh-malik.com/blog/deepseek-v4-flash-0731-benchmarks-cover.png) LLM Engineering • Aug 1, 2026 ### DeepSeek V4 Flash 0731 Benchmarks: 13B Active Beats 1.6T DeepSeek V4 Flash 0731 benchmarks: same 284B/13B architecture as the preview, re-post-trained only — and it beats the 1.6T V4-Pro Preview on nine agent tests. 9 min read Read more →](https://umesh-malik.com/blog/deepseek-v4-flash-0731-benchmarks) [![A RAG chatbot in Next.js: embed the query, search pgvector, augment the prompt, stream a cited answer](https://umesh-malik.com/blog/rag-chatbot-nextjs-guide-cover.png) AI Engineering • Jul 21, 2026 ### Build a RAG Chatbot in Next.js: Retrieval, Streaming & Citations (2026) Build a RAG chatbot in Next.js with the AI SDK: embed the query, search pgvector, stream a grounded answer with citations, and stop hallucinations. 8 min read Read more →](https://umesh-malik.com/blog/rag-chatbot-nextjs-guide) [![React Server Components and the use client boundary: server graph, client graph, and where the line is drawn](https://umesh-malik.com/blog/react-server-components-guide-cover.png) Web Engineering • Jul 21, 2026 ### React Server Components in 2026: The Mental Model, the use client Boundary & When Not to Use Them React Server Components in 2026: the mental model that finally clicks, the use client boundary rules, and when NOT to use them — with the Web Vitals payoff. 7 min read Read more →](https://umesh-malik.com/blog/react-server-components-guide) [![The production layer of a Vercel AI SDK app: streaming, tool-calling, abort, rate limiting, and cost control](https://umesh-malik.com/blog/vercel-ai-sdk-production-guide-cover.png) AI Engineering • Jul 21, 2026 ### Vercel AI SDK in Production: Streaming, Tool-Calling & the Gotchas Nobody Tells You (2026) Vercel AI SDK in production: streaming, tool-calling, aborting generations, error retry UX, rate limiting, and cost control — the layer every tutorial skips. 9 min read Read more →](https://umesh-malik.com/blog/vercel-ai-sdk-production-guide) [![Kimi K3 vs Claude Fable 5 head-to-head showing benchmarks, pricing, and where the open 2.8T model wins](https://umesh-malik.com/blog/kimi-k3-vs-fable-5-cover.png) LLM Engineering • Jul 19, 2026 ### Kimi K3 vs Claude Fable 5: When the Open Model Is Worth the Switch Kimi K3 beats Claude Fable 5 on cost by a wide margin and loses on agentic tasks. The benchmarks that decide it, and how to run K3 where it actually wins. 6 min read Read more →](https://umesh-malik.com/blog/kimi-k3-vs-claude-fable-5) [![Cover showing an HTML document streaming placeholder markers that get filled out of order by template-for elements, with no JavaScript](https://umesh-malik.com/blog/streaming-html-out-of-order-without-javascript-cover.png) Web Engineering • Jul 14, 2026 ### Streaming HTML Out of Order Without JavaScript (2026) Streaming HTML out of order without JavaScript: how Declarative Partial Updates and Declarative Shadow DOM reorder content natively in Chrome 148. 13 min read Read more →](https://umesh-malik.com/blog/streaming-html-out-of-order-without-javascript) [![ChatGPT super app reform showing the Apps SDK built on MCP with inline app UIs and the App Directory](https://umesh-malik.com/blog/chatgpt-apps-sdk-cover.png) AI Engineering • Jul 11, 2026 ### ChatGPT Apps SDK and the Super App Reform: How Apps in ChatGPT Work (2026) The ChatGPT Apps SDK explained: how apps in ChatGPT work, why it's built on MCP, who the launch partners are, and how developers build and submit apps. 7 min read Read more →](https://umesh-malik.com/blog/chatgpt-apps-sdk-super-app-guide) [![GPT-5.6 Sol vs Terra vs Luna comparison showing price, coding strength, and cost per task](https://umesh-malik.com/blog/gpt-5-6-sol-terra-luna-cover.png) LLM Engineering • Jul 11, 2026 ### GPT-5.6 Sol vs Terra vs Luna: The Routing Strategy That Cuts Cost GPT-5.6 Sol vs Terra vs Luna compared on price, coding, latency, and cost per task — plus a routing strategy that cuts your bill without wrecking quality. 5 min read Read more →](https://umesh-malik.com/blog/gpt-5-6-sol-vs-terra-vs-luna) [![OpenAI GPT-5.6 family showing Sol, Terra, and Luna tiers with benchmarks, pricing, and 1.05M context](https://umesh-malik.com/blog/gpt-5-6-cover.png) LLM Engineering • Jul 11, 2026 ### GPT-5.6 API: Pricing, Thinking Modes, and the Shared Context Trap GPT-5.6 API pricing ($1-$30/1M), the Ultra and Max thinking modes, and a 1.05M context window that is shared — with the fine print that breaks agent loops. 10 min read Read more →](https://umesh-malik.com/blog/openai-gpt-5-6-sol-terra-luna-guide) [![Editorial cover: build enterprise-grade AI agents for free with open-source MaxKB, $0 API cost, self-hosted](https://umesh-malik.com/blog/build-enterprise-ai-agents-free-cover.png) AI Engineering • Jul 8, 2026 ### How to Build Enterprise-Grade AI Agents for Free (MaxKB, 2026) How to build enterprise-grade AI agents for free in 2026: a hands-on MaxKB + local LLM guide to RAG precision, security, and $0 API cost. 10 min read Read more →](https://umesh-malik.com/blog/build-enterprise-ai-agents-free) [![Cover for the HTTP QUERY method guide: RFC 10008's safe, idempotent, cacheable request method with a body, explained for REST API designers](https://umesh-malik.com/blog/http-query-method-rfc-10008-guide-cover.png) Web Engineering • Jul 3, 2026 ### HTTP QUERY Method Explained (RFC 10008): GET vs POST RFC 10008's HTTP QUERY method is safe, idempotent, and cacheable like GET but carries a body like POST. What it fixes and where it works today. 9 min read Read more →](https://umesh-malik.com/blog/http-query-method-rfc-10008-guide) [![Cover for the Claude Fable 5 deep-dive guide: capabilities, the $10/$50 cost math, API behavior, and when to use Anthropic's most capable model](https://umesh-malik.com/blog/claude-fable-5-guide-cover.png) LLM Engineering • Jul 2, 2026 ### Claude Fable 5: Capabilities, Cost & When to Use It (2026) Claude Fable 5 is Anthropic's most capable model yet. The honest deep-dive: capabilities, the $10/$50 cost math, API behavior, and when to use it. 12 min read Read more →](https://umesh-malik.com/blog/claude-fable-5-guide) [![Cover for the Claude Sonnet 5 guide: benchmarks, pros and cons, use cases, and cost math versus Sonnet 4.6 and Opus 4.8](https://umesh-malik.com/blog/claude-sonnet-5-guide-cover.png) LLM Engineering • Jul 1, 2026 ### Claude Sonnet 5 for Coding: The Tokenizer Change That Moves Your Bill Claude Sonnet 5 for coding lands near Opus level at Sonnet prices — until the tokenizer change moves your bill. The real cost math, and when it beats Opus 4.8. 8 min read Read more →](https://umesh-malik.com/blog/claude-sonnet-5-guide) [![Field report cover: a week of running Claude Code auto mode in production, showing what it nailed, where it broke, and the cost](https://umesh-malik.com/blog/claude-code-auto-mode-production-field-report-cover.png) AI Coding Agents & DX • Jun 25, 2026 ### Is Claude Code Auto Mode Reliable in Production? A Field Report I ran Claude Code auto mode in production for a week — where it's reliable, where it broke, real token costs from my usage logs, and my honest verdict. 6 min read Read more →](https://umesh-malik.com/blog/claude-code-auto-mode-production-field-report) [![Decision matrix cover comparing Claude Code, Cursor, and GitHub Copilot for real production work in 2026](https://umesh-malik.com/blog/claude-code-vs-cursor-production-work-2026-cover.png) AI Coding Agents & DX • Jun 25, 2026 ### Claude Code vs Cursor for Production: A Shipping Engineer's Field Report (2026) Claude Code vs Cursor for production, field-tested on real shipping tasks: a working engineer's decision table, failure modes, pricing, and which to use when. 5 min read Read more →](https://umesh-malik.com/blog/claude-code-vs-cursor-production-work-2026) [![Cover comparing free and paid access to Claude Code, Codex, Gemini CLI, and GitHub Copilot AI coding agents in 2026](https://umesh-malik.com/blog/use-claude-code-codex-for-free-cover.png) AI Coding Agents & DX • Jun 23, 2026 ### Can You Use Claude Code and Codex for Free? Honest 2026 Guide The honest answer to using Claude Code and Codex for free in 2026: what's truly $0, what isn't, the best free AI coding CLIs, and how to cut your bill. 7 min read Read more →](https://umesh-malik.com/blog/use-claude-code-codex-for-free) [![Cover showing FastAPI's new app.frontend() method mounting a built SPA directory alongside API routes](https://umesh-malik.com/blog/fastapi-spa-app-frontend-explained-cover.png) Web Engineering • Jun 21, 2026 ### FastAPI Finally Has Native SPA Support: app.frontend() Explained FastAPI 0.138.0 ships app.frontend() — a native way to serve React, Vue, and Svelte SPA builds. How it works, real use cases, and what it still can't do. 8 min read Read more →](https://umesh-malik.com/blog/fastapi-spa-app-frontend-explained) [![The Agentic Browsing category in PageSpeed Insights scoring a website for AI agents alongside Performance, Accessibility, Best Practices and SEO](https://umesh-malik.com/blog/agentic-browsing-pagespeed-ai-ready-cover.png) AI Engineering • Jun 19, 2026 ### Agentic Browsing in PageSpeed Insights: How to Make Your Website AI-Ready (2026) Agentic browsing in PageSpeed Insights grades your site for AI agents, not just humans. What the category checks, why Google added it, how to pass it. 9 min read Read more →](https://umesh-malik.com/blog/agentic-browsing-pagespeed-ai-ready) [![Editorial cover: the demo-to-production gap for autonomous AI agents in 2026](https://umesh-malik.com/blog/autonomous-ai-agents-production-gap-2026-cover.png) AI Engineering • Jun 14, 2026 ### Why 77% of Autonomous AI Agents Never Reach Production (2026) Only 23% of autonomous AI agents reach production in 2026. The demo-to-production gap, why agents fail, and the playbook the winners actually use. 9 min read Read more →](https://umesh-malik.com/blog/autonomous-ai-agents-production-gap-2026) [![Cover showing the one-day flow of Claude Fable 5 building a streaming microservice: spec, infrastructure, code, and ship](https://umesh-malik.com/blog/claude-fable-5-streaming-microservice-one-day-cover.png) AI Coding Agents & DX • Jun 13, 2026 ### How I Built a Full Audio/Video Streaming Microservice in One Day with Claude Fable 5 Auto Mode Claude Fable 5 in auto mode built my entire HLS streaming microservice in under a day — AWS infra, security, backend, frontend, CI/CD, migrations, runbooks. 11 min read Read more →](https://umesh-malik.com/blog/claude-fable-5-streaming-microservice-one-day) [![The stages of a production retrieval-augmented generation pipeline](https://umesh-malik.com/blog/build-rag-pipeline-from-scratch-cover.png) AI Engineering • Jun 8, 2026 ### Build a RAG Pipeline From Scratch: Production Patterns That Matter Build a RAG pipeline from scratch: chunking, embeddings, retrieval, reranking, grounded generation, and the production patterns that decide whether it works. 7 min read Read more →](https://umesh-malik.com/blog/build-rag-pipeline-from-scratch) [![Comparison of Cursor, Claude Code, and GitHub Copilot AI coding tools](https://umesh-malik.com/blog/cursor-vs-claude-code-vs-copilot-cover.png) AI Coding Agents & DX • Jun 8, 2026 ### Cursor vs Claude Code vs Copilot (2026): Which Tool for What Cursor vs Claude Code vs Copilot in 2026 — how they actually differ in model, workflow, and autonomy, and which to use for what (I use all three). 5 min read Read more →](https://umesh-malik.com/blog/cursor-vs-claude-code-vs-copilot) [![Deploying a Model Context Protocol server to the edge on Cloudflare Workers](https://umesh-malik.com/blog/deploy-mcp-server-cloudflare-workers-cover.png) AI Engineering • Jun 8, 2026 ### Deploy an MCP Server on Cloudflare Workers (Free, at the Edge) Deploy an MCP server on Cloudflare Workers: wrangler.toml, the run\_worker\_first model, routing /mcp, local testing, and going live on the free tier. 7 min read Read more →](https://umesh-malik.com/blog/deploy-mcp-server-cloudflare-workers) [![Architecture of a production Model Context Protocol server on Cloudflare Workers](https://umesh-malik.com/blog/how-to-build-mcp-server-cover.png) AI Engineering • Jun 8, 2026 ### How to Build an MCP Server: A Step-by-Step Guide (2026) How to build an MCP server, step by step: JSON-RPC 2.0, the Streamable HTTP transport, typed tools, and agent discovery — from a real one I shipped. 9 min read Read more →](https://umesh-malik.com/blog/how-to-build-mcp-server) [![Anatomy of an effective CLAUDE.md project context file for Claude Code](https://umesh-malik.com/blog/how-to-write-claude-md-cover.png) AI Coding Agents & DX • Jun 8, 2026 ### How to Write a CLAUDE.md That Actually Helps How to write a CLAUDE.md that actually helps Claude Code: what to include, what to leave out, a real structure, and how to stop it from rotting. 7 min read Read more →](https://umesh-malik.com/blog/how-to-write-claude-md) [![claude-swap cover showing the four-step flow of switching Claude Code accounts: add account, switch, restore credentials, restart](https://umesh-malik.com/blog/claude-swap-multi-account-switcher-guide-cover.png) AI Coding Agents & DX • May 30, 2026 ### How to Switch Between Multiple Claude Code Accounts Without Re-Logging In (claude-swap Guide) claude-swap is an open-source CLI that switches Claude Code accounts in seconds — no browser re-login. How it works, how to use it, and what it misses. 15 min read Read more →](https://umesh-malik.com/blog/claude-swap-multi-account-switcher-guide) [![Claude Code source map leak visualization showing 512K lines of TypeScript escaping a code window with key stats](https://umesh-malik.com/blog/claude-code-leak-cover.png) AI Security • Apr 2, 2026 ### Claude Code Leak 2026: What Escaped and What Didn't The Claude Code leak of March 31, 2026, explained: what the source-map exposure revealed, Anthropic's DMCA sweep, and the fallout. 8 min read Read more →](https://umesh-malik.com/blog/claude-code-leak-march-2026) [![Editorial cover: the Axios npm supply-chain compromise (1.14.1 and 0.30.4)](https://umesh-malik.com/blog/axios-compromised-npm-cover.png) AI Security • Mar 31, 2026 ### Axios Compromised on npm: 1.14.1, 0.30.4 Drop a Cross-Platform RAT Axios compromised on npm on March 31, 2026: versions 1.14.1 and 0.30.4 dropped a cross-platform RAT. Verified timeline, impact, IOCs, and recovery. 4 min read Read more →](https://umesh-malik.com/blog/axios-compromised-npm-cross-platform-rat) [![Nvidia OpenClaw strategy cover showing task assignment, agent execution, guardrails, and enterprise runtime control](https://umesh-malik.com/blog/nvidia-openclaw-cover.png) AI Coding Agents & DX • Mar 17, 2026 ### Nvidia OpenClaw Explained: Your AI Agent Strategy (GTC 2026) At GTC 2026, Jensen Huang said every company needs a Nvidia OpenClaw strategy. Here is what it means and what U.S. teams should do next. 6 min read Read more →](https://umesh-malik.com/blog/nvidia-openclaw-strategy-ai-agent-plan) [![ChatGPT adult mode cover showing age prediction, adult verification, text-only scope, and safety guardrails](https://umesh-malik.com/blog/chatgpt-adult-mode-cover.png) LLM Engineering • Mar 16, 2026 ### ChatGPT Adult Mode: Is It Live Yet? (Status Explained) ChatGPT adult mode is still delayed — OpenAI's official status, what the feature would allow, why it was pushed back, and answers for parents. 7 min read Read more →](https://umesh-malik.com/blog/chatgpt-adult-mode-delay-guide) [![ChatGPT interactive learning cover showing math and science concepts becoming visual and interactive inside ChatGPT](https://umesh-malik.com/blog/chatgpt-learning-visuals-cover.png) LLM Engineering • Mar 12, 2026 ### ChatGPT Interactive Math and Science Visuals: What to Know ChatGPT interactive math and science visuals launched in March 2026: how the new learning modules work, who gets access, and why students benefit. 6 min read Read more →](https://umesh-malik.com/blog/chatgpt-interactive-math-science-visuals-guide) [![Anthropic Code Review cover showing multi-agent pull request review across repository context and custom review rules](https://umesh-malik.com/blog/anthropic-code-review-cover.png) AI Coding Agents & DX • Mar 10, 2026 ### Claude Code Review: How It Works, Pricing & Setup Anthropic's Claude Code Review runs multi-agent PR reviews for $15-$25 each. How it works, pricing, REVIEW.md setup, and where it beats linters. 6 min read Read more →](https://umesh-malik.com/blog/anthropic-code-review-claude-code-guide) [![Agentic AI enterprise security cover showing identity, prompt injection, policy gates, and observability](https://umesh-malik.com/blog/agentic-ai-enterprise-security-cover.png) AI Security • Mar 9, 2026 ### Agentic AI Security: The New Enterprise Control Model Agentic AI security breaks the old enterprise trust model. How to fix identity, delegated authority, prompt injection defense, and tool-level policy in 2026. 8 min read Read more →](https://umesh-malik.com/blog/agentic-ai-enterprise-security-model) [![OpenAI GPT-5.4 overview showing professional work, coding, computer use, and 1M context](https://umesh-malik.com/blog/gpt-5-4-cover.png) LLM Engineering • Mar 6, 2026 ### GPT-5.4 for Agents: Computer Use, MCP Tool Calls, and Real Pricing GPT-5.4's native computer use and MCP tool calls are the real upgrade for agents. What holds up in a loop, what the 1M context costs, and how Pro compares. 12 min read Read more →](https://umesh-malik.com/blog/openai-gpt-5-4-complete-guide) [![OpenAI GPT-5.3 Instant overview showing three key improvements: fewer refusals, better web answers, and smoother conversational tone](https://umesh-malik.com/blog/gpt-5-3-instant-cover.png) LLM Engineering • Mar 4, 2026 ### OpenAI GPT-5.3 Instant: 26.8% Fewer Hallucinations, Reduced Refusals, and Better Web Answers GPT-5.3 Instant brings 26.8% fewer hallucinations, fewer needless refusals, and better web-sourced answers — what changed and why it matters for devs. 10 min read Read more →](https://umesh-malik.com/blog/openai-gpt-5-3-instant-fewer-refusals-better-answers) [![DeepSeek V4 launch preview showing AI model race between China-first chips and U.S. rivals](https://umesh-malik.com/blog/deepseek-v4-release-cover.png) LLM Engineering • Mar 1, 2026 ### DeepSeek V4 vs US AI Models: Benchmarks, Architecture, and What It Means for the Industry DeepSeek V4 is expected in early March 2026. Here is what is confirmed, what remains unverified, and how it challenges U.S. AI rivals. 10 min read Read more →](https://umesh-malik.com/blog/deepseek-v4-release-challenge-us-ai-rivals) [![RAG vs fine-tuning architecture comparison for LLMs](https://umesh-malik.com/blog/rag-vs-fine-tuning-llms-2026-cover.png) AI Engineering • Feb 28, 2026 ### RAG vs Fine-Tuning for LLMs in 2026: A Production Decision Framework With Real Tradeoffs RAG vs fine-tuning for LLMs in 2026: a practical decision framework covering architecture tradeoffs, cost, latency, and when to use each in production. 6 min read Read more →](https://umesh-malik.com/blog/rag-vs-fine-tuning-llms-2026) [![Editorial cover: converting Figma designs to React with OpenAI Codex](https://umesh-malik.com/blog/figma-codex-react-cover.png) AI Coding Agents & DX • Feb 27, 2026 ### Figma to React With OpenAI Codex: A 2026 Guide A 2026 guide to Figma to React conversion with OpenAI Codex: setup, prompts, component structure, and real production examples. 3 min read Read more →](https://umesh-malik.com/blog/figma-codex-react-2026) [![A lightning bolt splitting between Next.js and Vite logos, symbolizing Cloudflare's revolutionary Vinext framework that's 4.4x faster](https://umesh-malik.com/blog/cloudflare-vinext-cover.png) Web Engineering • Feb 25, 2026 ### Cloudflare viNext: The $1,100 Next.js-on-Vite Rebuild Cloudflare viNext rebuilt Next.js on Vite for $1,100 in 7 days: 4.4x faster builds, 57% smaller bundles, already powering CIO.gov in production. 27 min read Read more →](https://umesh-malik.com/blog/cloudflare-vinext-next-js-vite-revolution) [![A glowing AI brain being extracted through a network of fraudulent connections representing the massive distillation attack on Claude](https://umesh-malik.com/blog/distillation-attacks-cover.png) AI Security • Feb 24, 2026 ### AI Model Distillation: Inside the $100M Claude Heist Anthropic exposes an AI model distillation attack by DeepSeek, Moonshot, and MiniMax: 16 million exchanges, 24,000 fake accounts. The forensic breakdown. 33 min read Read more →](https://umesh-malik.com/blog/anthropic-detecting-preventing-distillation-attacks) [![A desktop workstation running a local LLM for coding — 80 billion parameters, 3 billion active — representing the shift from cloud AI to local AI coding](https://umesh-malik.com/blog/local-llm-coding-cover.png) AI Coding Agents & DX • Feb 22, 2026 ### Qwen3-Coder: Run an 80B-Parameter LLM on Your Desktop Qwen3-Coder runs 80B parameters on a desktop with only 3B active per token — and plugs into Claude Code. Why the cloud-only era of AI coding is ending. 16 min read Read more →](https://umesh-malik.com/blog/local-llm-coding-revolution-qwen3-coder-desktop) [![Three AI coding agents — database, security, and test — sitting at terminal screens writing and reviewing code, all guided by a central SPEC.md specification document](https://umesh-malik.com/blog/spec-driven-dev-cover.png) AI Coding Agents & DX • Feb 21, 2026 ### Spec-Driven Development for AI Agents (Addy Osmani) Why AI coding agent prompts fail — and how spec-driven development fixes it, per Addy Osmani's 5-principle framework backed by GitHub's 2,500-config analysis. 19 min read Read more →](https://umesh-malik.com/blog/spec-driven-development-ai-agents-addy-osmani) [![Editorial cover: Node.js V8 pointer compression cuts heap memory in half](https://umesh-malik.com/blog/nodejs-memory-cut-in-half-cover.png) Web Engineering • Feb 18, 2026 ### Node.js Pointer Compression: Cut Heap Memory ~50% V8 pointer compression finally lands in Node.js: one Docker image swap cuts heap memory ~50%, improves P99 latency, and can save $80K-$300K a year. 17 min read Read more →](https://umesh-malik.com/blog/nodejs-memory-cut-in-half-pointer-compression) [![AGENTS.md study results showing a document icon next to a declining performance chart from ETH Zurich's 138-repo benchmark](https://umesh-malik.com/blog/agents-md-cover.png) AI Coding Agents & DX • Feb 17, 2026 ### AGENTS.md Files Don't Work the Way You Think — A 138-Repo Study A 138-repo study: AGENTS.md files hurt performance by 2-3% and raised costs 20%+. What the research found — and what actually works instead. 12 min read Read more →](https://umesh-malik.com/blog/agents-md-ai-coding-agents-study) [![Docker Swarm versus Kubernetes cost comparison: $166 per year simple setup versus $200K complex infrastructure](https://umesh-malik.com/blog/docker-swarm-vs-k8s-cover.png) Web Engineering • Feb 17, 2026 ### Docker Swarm vs Kubernetes: $166/yr Beats a $200K Cluster Docker Swarm vs Kubernetes: a live SaaS runs for $166/year with zero crashes in 10 years, while the average Kubernetes cluster wastes 87% of its CPU. 20 min read Read more →](https://umesh-malik.com/blog/docker-swarm-vs-kubernetes-166-dollar-reality-check) [![The Seedance 2.0 crisis: Hollywood confrontation with AI-generated video showing film reel colliding with AI](https://umesh-malik.com/blog/seedance-cover.png) LLM Engineering • Feb 16, 2026 ### Seedance 2.0: The Two-Line Prompt That Broke Hollywood ByteDance's Seedance 2.0 made a photorealistic Tom Cruise vs Brad Pitt fight from a two-line prompt — igniting Disney, Paramount, and SAG-AFTRA backlash. 13 min read Read more →](https://umesh-malik.com/blog/seedance-2-hollywood-ai-copyright-crisis) [![Editorial cover: an AI agent's autonomous retaliation against an open-source maintainer](https://umesh-malik.com/blog/ai-agent-matplotlib-cover.png) AI Security • Feb 15, 2026 ### AI Agent Attacks Developer After Matplotlib PR Rejection — Full Story The first documented AI agent attack on an open-source maintainer: rejected on a matplotlib PR, the bot published a hit piece. Full story and lessons. 10 min read Read more →](https://umesh-malik.com/blog/ai-agent-attacks-developer-matplotlib-open-source) [![Node.js backend architecture showing Express server, middleware chain, REST API endpoints, and database layer](https://umesh-malik.com/blog/nodejs-backend-cover.png) Web Engineering • Feb 10, 2026 ### Node.js Backend for Frontend Developers: A Practical Guide A frontend developer's guide to building a Node.js backend: Express, REST APIs, middleware, databases, auth, and deployment — plus the mindset shift you need. 8 min read Read more →](https://umesh-malik.com/blog/nodejs-backend-for-frontend-developers) [![Frontend career growth timeline showing progression from Associate Engineer through to SDE-2 at Expedia Group](https://umesh-malik.com/blog/frontend-career-cover.png) Career & Productivity • Jan 8, 2026 ### Frontend Career Growth: From Junior to Senior Engineer From Associate Engineer to SDE-2: what actually drives frontend career growth — technical skills, soft skills, and the things nobody tells you. 5 min read Read more →](https://umesh-malik.com/blog/frontend-career-growth-junior-to-senior) [![Core Web Vitals dashboard showing three gauge meters for LCP, INP, and CLS with before and after optimization results](https://umesh-malik.com/blog/core-web-vitals-cover.png) Web Engineering • Nov 12, 2025 ### How to Fix Core Web Vitals: LCP, INP & CLS (2026) A hands-on guide to optimizing Core Web Vitals (LCP, INP, CLS). Covers measurement, diagnosis, and specific fixes with before/after examples from real projects. 6 min read Read more →](https://umesh-malik.com/blog/core-web-vitals-optimization-guide) [![Developer productivity workspace showing a terminal, editor, and organized workflow system for senior engineers](https://umesh-malik.com/blog/dev-productivity-cover.png) Career & Productivity • Sep 5, 2025 ### Developer Productivity Tools for Senior Engineers A senior engineer's real stack of developer productivity tools — editor, terminal, code review habits, and focus systems that cut daily friction. 4 min read Read more →](https://umesh-malik.com/blog/developer-productivity-tools-senior-engineers) [![Frontend testing trophy model with layers for static analysis, integration tests, unit tests, and E2E tests](https://umesh-malik.com/blog/frontend-testing-cover.png) Web Engineering • Jul 10, 2025 ### Frontend Testing Strategies That Actually Work in 2026 Practical frontend testing strategies for 2025: component tests, integration, E2E, and the patterns that give the most confidence per line. 5 min read Read more →](https://umesh-malik.com/blog/frontend-testing-strategies-2025) [![TailwindCSS v4 migration showing the shift from JavaScript config to CSS-first @theme configuration](https://umesh-malik.com/blog/tailwindcss-v4-cover.png) Web Engineering • May 20, 2025 ### TailwindCSS v4 Migration Guide: Breaking Changes & the @theme Config TailwindCSS v4 migration, done right: every breaking change, the new CSS-first @theme config that replaces tailwind.config.js, and a step-by-step upgrade path. 3 min read Read more →](https://umesh-malik.com/blog/tailwindcss-v4-migration-guide) [![JavaScript ES2024 features overview showing Object.groupBy, Promise.withResolvers, Unicode strings, and RegExp v flag](https://umesh-malik.com/blog/javascript-es2024-cover.png) Web Engineering • Mar 15, 2025 ### ES2024 Features You'll Actually Use in JavaScript The most impactful ES2024 features: Array grouping, Promise.withResolvers, well-formed Unicode strings, and the RegExp v flag — with practical examples. 5 min read Read more →](https://umesh-malik.com/blog/javascript-es2024-features-you-should-know) [![TypeScript utility types overview showing Partial, Required, Pick, Omit, and Record with code examples](https://umesh-malik.com/blog/typescript-utility-cover.png) Web Engineering • Dec 15, 2024 ### TypeScript Utility Types: Complete Guide to Partial, Required, Pick, Omit, Record, and More (2026) TypeScript utility types explained: Partial, Pick, Omit, Record, Exclude, ReturnType and more — with real examples, a cheat sheet, and common pitfalls. 9 min read Read more →](https://umesh-malik.com/blog/typescript-utility-types-complete-guide) [![React performance optimization showing 10 techniques including memoization, code splitting, and virtualization](https://umesh-malik.com/blog/react-performance-cover.png) Web Engineering • Nov 20, 2024 ### React Performance Optimization: 10 Proven Techniques React performance optimization techniques — memoization, code splitting, virtualization, and 7 more battle-tested strategies from real apps. 5 min read Read more →](https://umesh-malik.com/blog/react-performance-optimization-techniques) [![SvelteKit versus Next.js framework comparison across performance, developer experience, routing, and ecosystem](https://umesh-malik.com/blog/sveltekit-vs-nextjs-cover.png) Web Engineering • Oct 10, 2024 ### SvelteKit vs Next.js 2026: Which Should You Choose? SvelteKit vs Next.js: an in-depth 2026 comparison of performance, DX, routing, and deployment, from real production experience. 5 min read Read more →](https://umesh-malik.com/blog/sveltekit-vs-nextjs-comparison) Google Search · Preferred sources ## Prefer this site on Google If you already read this writing, add umesh-malik.com as a Preferred Source. Google can then highlight it with a preferred badge in Top Stories, AI Overviews, and AI Mode — for you, not as a site-wide ranking boost. [Open in Google Search(opens Google Preferred Sources in a new tab)](https://www.google.com/preferences/source?q=umesh-malik.com) ## Popular Tags [Vulnerability Management](https://umesh-malik.com/blog/tag/vulnerability-management)[Performance Engineering](https://umesh-malik.com/blog/tag/performance-engineering)[Content Security Policy](https://umesh-malik.com/blog/tag/content-security-policy)[React Server Components](https://umesh-malik.com/blog/tag/react-server-components)[Confidential Computing](https://umesh-malik.com/blog/tag/confidential-computing)[Developer Productivity](https://umesh-malik.com/blog/tag/developer-productivity)[Reinforcement Learning](https://umesh-malik.com/blog/tag/reinforcement-learning)[Production Engineering](https://umesh-malik.com/blog/tag/production-engineering)[Model Context Protocol](https://umesh-malik.com/blog/tag/model-context-protocol)[Supply Chain Security](https://umesh-malik.com/blog/tag/supply-chain-security)[AI Coding Agents & DX](https://umesh-malik.com/blog/tag/ai-coding-agents-dx)[Computational Biology](https://umesh-malik.com/blog/tag/computational-biology)[supply-chain-security](https://umesh-malik.com/blog/tag/supply-chain-security)[dependency-management](https://umesh-malik.com/blog/tag/dependency-management)[LLM Cost Optimization](https://umesh-malik.com/blog/tag/llm-cost-optimization)[LLM cost optimization](https://umesh-malik.com/blog/tag/llm-cost-optimization)[Distributed Training](https://umesh-malik.com/blog/tag/distributed-training)[Backend Architecture](https://umesh-malik.com/blog/tag/backend-architecture)[Platform Engineering](https://umesh-malik.com/blog/tag/platform-engineering)[Engineering Practice](https://umesh-malik.com/blog/tag/engineering-practice)[Differential Privacy](https://umesh-malik.com/blog/tag/differential-privacy)[Speculative Decoding](https://umesh-malik.com/blog/tag/speculative-decoding)[developer-experience](https://umesh-malik.com/blog/tag/developer-experience)[platform-engineering](https://umesh-malik.com/blog/tag/platform-engineering)[Developer Experience](https://umesh-malik.com/blog/tag/developer-experience)[Open Source Security](https://umesh-malik.com/blog/tag/open-source-security)[Frontend Performance](https://umesh-malik.com/blog/tag/frontend-performance)[Software Engineering](https://umesh-malik.com/blog/tag/software-engineering)[Memory Optimization](https://umesh-malik.com/blog/tag/memory-optimization)[Systems Programming](https://umesh-malik.com/blog/tag/systems-programming)[Privacy Engineering](https://umesh-malik.com/blog/tag/privacy-engineering)[Reverse Engineering](https://umesh-malik.com/blog/tag/reverse-engineering)[Engineering Culture](https://umesh-malik.com/blog/tag/engineering-culture)[Context Engineering](https://umesh-malik.com/blog/tag/context-engineering)[Threat Intelligence](https://umesh-malik.com/blog/tag/threat-intelligence)[AI Pair Programming](https://umesh-malik.com/blog/tag/ai-pair-programming)[Enterprise Security](https://umesh-malik.com/blog/tag/enterprise-security)[Design to Code 2026](https://umesh-malik.com/blog/tag/design-to-code-2026)[Content Provenance](https://umesh-malik.com/blog/tag/content-provenance)[Agent Architecture](https://umesh-malik.com/blog/tag/agent-architecture)[Information Theory](https://umesh-malik.com/blog/tag/information-theory)[Cloudflare Workers](https://umesh-malik.com/blog/tag/cloudflare-workers)[Prompt Engineering](https://umesh-malik.com/blog/tag/prompt-engineering)[LLM Infrastructure](https://umesh-malik.com/blog/tag/llm-infrastructure)[agent-architecture](https://umesh-malik.com/blog/tag/agent-architecture)[PageSpeed Insights](https://umesh-malik.com/blog/tag/pagespeed-insights)[React Architecture](https://umesh-malik.com/blog/tag/react-architecture)[AI Infrastructure](https://umesh-malik.com/blog/tag/ai-infrastructure)[Developer Tooling](https://umesh-malik.com/blog/tag/developer-tooling)[Incident Response](https://umesh-malik.com/blog/tag/incident-response)[Technical Writing](https://umesh-malik.com/blog/tag/technical-writing)[Cost Optimization](https://umesh-malik.com/blog/tag/cost-optimization)[LLM Failure Modes](https://umesh-malik.com/blog/tag/llm-failure-modes)[Human in the Loop](https://umesh-malik.com/blog/tag/human-in-the-loop)[Generative Models](https://umesh-malik.com/blog/tag/generative-models)[HTTP QUERY Method](https://umesh-malik.com/blog/tag/http-query-method)[AI UI Development](https://umesh-malik.com/blog/tag/ai-ui-development)[National Security](https://umesh-malik.com/blog/tag/national-security)[Content Strategy](https://umesh-malik.com/blog/tag/content-strategy)[AI Coding Agents](https://umesh-malik.com/blog/tag/ai-coding-agents)[Google Workspace](https://umesh-malik.com/blog/tag/google-workspace)[Linear Attention](https://umesh-malik.com/blog/tag/linear-attention)[Bot Verification](https://umesh-malik.com/blog/tag/bot-verification)[Model Evaluation](https://umesh-malik.com/blog/tag/model-evaluation)[Patch Management](https://umesh-malik.com/blog/tag/patch-management)[Trust and Safety](https://umesh-malik.com/blog/tag/trust-and-safety)[Agent Governance](https://umesh-malik.com/blog/tag/agent-governance)[Model Comparison](https://umesh-malik.com/blog/tag/model-comparison)[Vector Databases](https://umesh-malik.com/blog/tag/vector-databases)[Machine Learning](https://umesh-malik.com/blog/tag/machine-learning)[Agentic Browsing](https://umesh-malik.com/blog/tag/agentic-browsing)[AI in Production](https://umesh-malik.com/blog/tag/ai-in-production)[Prompt Injection](https://umesh-malik.com/blog/tag/prompt-injection)[Web Engineering](https://umesh-malik.com/blog/tag/web-engineering)[LLM Engineering](https://umesh-malik.com/blog/tag/llm-engineering)[GPU Programming](https://umesh-malik.com/blog/tag/gpu-programming)[Data Governance](https://umesh-malik.com/blog/tag/data-governance)[Web Performance](https://umesh-malik.com/blog/tag/web-performance)[llm-engineering](https://umesh-malik.com/blog/tag/llm-engineering)[Abuse Detection](https://umesh-malik.com/blog/tag/abuse-detection)[Computer Vision](https://umesh-malik.com/blog/tag/computer-vision)[Core Web Vitals](https://umesh-malik.com/blog/tag/core-web-vitals)[Developer Tools](https://umesh-malik.com/blog/tag/developer-tools)[REST API Design](https://umesh-malik.com/blog/tag/rest-api-design)[Claude Sonnet 5](https://umesh-malik.com/blog/tag/claude-sonnet-5)[Video Streaming](https://umesh-malik.com/blog/tag/video-streaming)[AI Architecture](https://umesh-malik.com/blog/tag/ai-architecture)[AI Coding Tools](https://umesh-malik.com/blog/tag/ai-coding-tools)[Cloud Computing](https://umesh-malik.com/blog/tag/cloud-computing)[AI Engineering](https://umesh-malik.com/blog/tag/ai-engineering)[Bot Management](https://umesh-malik.com/blog/tag/bot-management)[Edge Computing](https://umesh-malik.com/blog/tag/edge-computing)[Infrastructure](https://umesh-malik.com/blog/tag/infrastructure)[Authentication](https://umesh-malik.com/blog/tag/authentication)[Virtualization](https://umesh-malik.com/blog/tag/virtualization)[GitHub Copilot](https://umesh-malik.com/blog/tag/github-copilot)[Insider Threat](https://umesh-malik.com/blog/tag/insider-threat)[Access Control](https://umesh-malik.com/blog/tag/access-control)[Claude Fable 5](https://umesh-malik.com/blog/tag/claude-fable-5)[Figma to React](https://umesh-malik.com/blog/tag/figma-to-react)[Agent Harness](https://umesh-malik.com/blog/tag/agent-harness)[Browser Tools](https://umesh-malik.com/blog/tag/browser-tools)[Observability](https://umesh-malik.com/blog/tag/observability)[Enterprise IT](https://umesh-malik.com/blog/tag/enterprise-it)[Documentation](https://umesh-malik.com/blog/tag/documentation)[LLM Inference](https://umesh-malik.com/blog/tag/llm-inference)[Apple Silicon](https://umesh-malik.com/blog/tag/apple-silicon)[Claude Opus 5](https://umesh-malik.com/blog/tag/claude-opus-5)[SQL Injection](https://umesh-malik.com/blog/tag/sql-injection)[agent-harness](https://umesh-malik.com/blog/tag/agent-harness)[observability](https://umesh-malik.com/blog/tag/observability)[Trade Secrets](https://umesh-malik.com/blog/tag/trade-secrets)[Audit Logging](https://umesh-malik.com/blog/tag/audit-logging)[Post-Training](https://umesh-malik.com/blog/tag/post-training)[Vercel AI SDK](https://umesh-malik.com/blog/tag/vercel-ai-sdk)[Web Standards](https://umesh-malik.com/blog/tag/web-standards)[Microservices](https://umesh-malik.com/blog/tag/microservices)[Enterprise AI](https://umesh-malik.com/blog/tag/enterprise-ai)[Online Safety](https://umesh-malik.com/blog/tag/online-safety)[Consumer Tech](https://umesh-malik.com/blog/tag/consumer-tech)[Pull Requests](https://umesh-malik.com/blog/tag/pull-requests)[Web Crawlers](https://umesh-malik.com/blog/tag/web-crawlers)[Self-Hosting](https://umesh-malik.com/blog/tag/self-hosting)[Tool Calling](https://umesh-malik.com/blog/tag/tool-calling)[Benchmarking](https://umesh-malik.com/blog/tag/benchmarking)[Productivity](https://umesh-malik.com/blog/tag/productivity)[Tail Latency](https://umesh-malik.com/blog/tag/tail-latency)[Neuroscience](https://umesh-malik.com/blog/tag/neuroscience)[Long Context](https://umesh-malik.com/blog/tag/long-context)[Agent Design](https://umesh-malik.com/blog/tag/agent-design)[On-Device ML](https://umesh-malik.com/blog/tag/on-device-ml)[Quantization](https://umesh-malik.com/blog/tag/quantization)[Open Weights](https://umesh-malik.com/blog/tag/open-weights)[Supply Chain](https://umesh-malik.com/blog/tag/supply-chain)[Scaling Laws](https://umesh-malik.com/blog/tag/scaling-laws)[Web Platform](https://umesh-malik.com/blog/tag/web-platform)[OpenAI Codex](https://umesh-malik.com/blog/tag/openai-codex)[Performance](https://umesh-malik.com/blog/tag/performance)[AI Security](https://umesh-malik.com/blog/tag/ai-security)[AI Training](https://umesh-malik.com/blog/tag/ai-training)[Claude Code](https://umesh-malik.com/blog/tag/claude-code)[WebAssembly](https://umesh-malik.com/blog/tag/webassembly)[Code Review](https://umesh-malik.com/blog/tag/code-review)[Prototyping](https://umesh-malik.com/blog/tag/prototyping)[Agentic Web](https://umesh-malik.com/blog/tag/agentic-web)[Simulations](https://umesh-malik.com/blog/tag/simulations)[AI Research](https://umesh-malik.com/blog/tag/ai-research)[Permissions](https://umesh-malik.com/blog/tag/permissions)[Tool Design](https://umesh-malik.com/blog/tag/tool-design)[parallelism](https://umesh-malik.com/blog/tag/parallelism)[Fine-Tuning](https://umesh-malik.com/blog/tag/fine-tuning)[Open Source](https://umesh-malik.com/blog/tag/open-source)[Offboarding](https://umesh-malik.com/blog/tag/offboarding)[Moonshot AI](https://umesh-malik.com/blog/tag/moonshot-ai)[API Caching](https://umesh-malik.com/blog/tag/api-caching)[Geopolitics](https://umesh-malik.com/blog/tag/geopolitics)[Build Tools](https://umesh-malik.com/blog/tag/build-tools)[TailwindCSS](https://umesh-malik.com/blog/tag/tailwindcss)[Type Safety](https://umesh-malik.com/blog/tag/type-safety)[Networking](https://umesh-malik.com/blog/tag/networking)[Cloudflare](https://umesh-malik.com/blog/tag/cloudflare)[robots.txt](https://umesh-malik.com/blog/tag/robots-txt)[API Design](https://umesh-malik.com/blog/tag/api-design)[Sandboxing](https://umesh-malik.com/blog/tag/sandboxing)[Automation](https://umesh-malik.com/blog/tag/automation)[Monitoring](https://umesh-malik.com/blog/tag/monitoring)[PostgreSQL](https://umesh-malik.com/blog/tag/postgresql)[LLM Agents](https://umesh-malik.com/blog/tag/llm-agents)[Algorithms](https://umesh-malik.com/blog/tag/algorithms)[Connectome](https://umesh-malik.com/blog/tag/connectome)[Zero Trust](https://umesh-malik.com/blog/tag/zero-trust)[Evaluation](https://umesh-malik.com/blog/tag/evaluation)[Kubernetes](https://umesh-malik.com/blog/tag/kubernetes)[Bare Metal](https://umesh-malik.com/blog/tag/bare-metal)[SQLAlchemy](https://umesh-malik.com/blog/tag/sqlalchemy)[Claude API](https://umesh-malik.com/blog/tag/claude-api)[Benchmarks](https://umesh-malik.com/blog/tag/benchmarks)[Workers AI](https://umesh-malik.com/blog/tag/workers-ai)[dependabot](https://umesh-malik.com/blog/tag/dependabot)[cloudflare](https://umesh-malik.com/blog/tag/cloudflare)[typescript](https://umesh-malik.com/blog/tag/typescript)[Compliance](https://umesh-malik.com/blog/tag/compliance)[Production](https://umesh-malik.com/blog/tag/production)[GenAI 2026](https://umesh-malik.com/blog/tag/genai-2026)[Agentic AI](https://umesh-malik.com/blog/tag/agentic-ai)[Gemini CLI](https://umesh-malik.com/blog/tag/gemini-cli)[Embeddings](https://umesh-malik.com/blog/tag/embeddings)[AI Tooling](https://umesh-malik.com/blog/tag/ai-tooling)[JavaScript](https://umesh-malik.com/blog/tag/javascript)[TypeScript](https://umesh-malik.com/blog/tag/typescript)[ECMAScript](https://umesh-malik.com/blog/tag/ecmascript)[Migration](https://umesh-malik.com/blog/tag/migration)[AI Ethics](https://umesh-malik.com/blog/tag/ai-ethics)[Inference](https://umesh-malik.com/blog/tag/inference)[AI Search](https://umesh-malik.com/blog/tag/ai-search)[Debugging](https://umesh-malik.com/blog/tag/debugging)[Compilers](https://umesh-malik.com/blog/tag/compilers)[Databases](https://umesh-malik.com/blog/tag/databases)[AI Policy](https://umesh-malik.com/blog/tag/ai-policy)[AI Agents](https://umesh-malik.com/blog/tag/ai-agents)[llama.cpp](https://umesh-malik.com/blog/tag/llama-cpp)[Local LLM](https://umesh-malik.com/blog/tag/local-llm)[Datasette](https://umesh-malik.com/blog/tag/datasette)[workflows](https://umesh-malik.com/blog/tag/workflows)[Diffusion](https://umesh-malik.com/blog/tag/diffusion)[Anthropic](https://umesh-malik.com/blog/tag/anthropic)[Streaming](https://umesh-malik.com/blog/tag/streaming)[RFC 10008](https://umesh-malik.com/blog/tag/rfc-10008)[Auto Mode](https://umesh-malik.com/blog/tag/auto-mode)[Starlette](https://umesh-malik.com/blog/tag/starlette)[Terraform](https://umesh-malik.com/blog/tag/terraform)[CLAUDE.md](https://umesh-malik.com/blog/tag/claude-md)[DevSecOps](https://umesh-malik.com/blog/tag/devsecops)[Education](https://umesh-malik.com/blog/tag/education)[AI Safety](https://umesh-malik.com/blog/tag/ai-safety)[Hollywood](https://umesh-malik.com/blog/tag/hollywood)[Copyright](https://umesh-malik.com/blog/tag/copyright)[ByteDance](https://umesh-malik.com/blog/tag/bytedance)[Deepfakes](https://umesh-malik.com/blog/tag/deepfakes)[SvelteKit](https://umesh-malik.com/blog/tag/sveltekit)[Security](https://umesh-malik.com/blog/tag/security)[KV Cache](https://umesh-malik.com/blog/tag/kv-cache)[Learning](https://umesh-malik.com/blog/tag/learning)[llms.txt](https://umesh-malik.com/blog/tag/llms-txt)[Payments](https://umesh-malik.com/blog/tag/payments)[Training](https://umesh-malik.com/blog/tag/training)[Research](https://umesh-malik.com/blog/tag/research)[DeepSeek](https://umesh-malik.com/blog/tag/deepseek)[Browsers](https://umesh-malik.com/blog/tag/browsers)[Apps SDK](https://umesh-malik.com/blog/tag/apps-sdk)[Wrangler](https://umesh-malik.com/blog/tag/wrangler)[OpenClaw](https://umesh-malik.com/blog/tag/openclaw)[NemoClaw](https://umesh-malik.com/blog/tag/nemoclaw)[Students](https://umesh-malik.com/blog/tag/students)[Frontend](https://umesh-malik.com/blog/tag/frontend)[Workflow](https://umesh-malik.com/blog/tag/workflow)[Meta AI](https://umesh-malik.com/blog/tag/meta-ai)[Windows](https://umesh-malik.com/blog/tag/windows)[ChatGPT](https://umesh-malik.com/blog/tag/chatgpt)[Privacy](https://umesh-malik.com/blog/tag/privacy)[Storage](https://umesh-malik.com/blog/tag/storage)[GPT-5.6](https://umesh-malik.com/blog/tag/gpt-5-6)[Testing](https://umesh-malik.com/blog/tag/testing)[Next.js](https://umesh-malik.com/blog/tag/next-js)[Kimi K3](https://umesh-malik.com/blog/tag/kimi-k3)[GraphQL](https://umesh-malik.com/blog/tag/graphql)[FastAPI](https://umesh-malik.com/blog/tag/fastapi)[Backend](https://umesh-malik.com/blog/tag/backend)[Node.js](https://umesh-malik.com/blog/tag/node-js)[Malware](https://umesh-malik.com/blog/tag/malware)[Parents](https://umesh-malik.com/blog/tag/parents)[Science](https://umesh-malik.com/blog/tag/science)[GPT-5.4](https://umesh-malik.com/blog/tag/gpt-5-4)[OpenAI](https://umesh-malik.com/blog/tag/openai)[Python](https://umesh-malik.com/blog/tag/python)[DevOps](https://umesh-malik.com/blog/tag/devops)[Docker](https://umesh-malik.com/blog/tag/docker)[Vercel](https://umesh-malik.com/blog/tag/vercel)[Gemini](https://umesh-malik.com/blog/tag/gemini)[ffmpeg](https://umesh-malik.com/blog/tag/ffmpeg)[Chrome](https://umesh-malik.com/blog/tag/chrome)[Kernel](https://umesh-malik.com/blog/tag/kernel)[SQLite](https://umesh-malik.com/blog/tag/sqlite)[github](https://umesh-malik.com/blog/tag/github)[python](https://umesh-malik.com/blog/tag/python)[Claude](https://umesh-malik.com/blog/tag/claude)[Cursor](https://umesh-malik.com/blog/tag/cursor)[NVIDIA](https://umesh-malik.com/blog/tag/nvidia)[EdTech](https://umesh-malik.com/blog/tag/edtech)[GitHub](https://umesh-malik.com/blog/tag/github)[Huawei](https://umesh-malik.com/blog/tag/huawei)[Career](https://umesh-malik.com/blog/tag/career)[Growth](https://umesh-malik.com/blog/tag/growth)[Vitest](https://umesh-malik.com/blog/tag/vitest)[ES2024](https://umesh-malik.com/blog/tag/es2024)[OAuth](https://umesh-malik.com/blog/tag/oauth)[CI/CD](https://umesh-malik.com/blog/tag/ci-cd)[macOS](https://umesh-malik.com/blog/tag/macos)[Evals](https://umesh-malik.com/blog/tag/evals)[Linux](https://umesh-malik.com/blog/tag/linux)[Metal](https://umesh-malik.com/blog/tag/metal)[ci-cd](https://umesh-malik.com/blog/tag/ci-cd)[React](https://umesh-malik.com/blog/tag/react)[MaxKB](https://umesh-malik.com/blog/tag/maxkb)[DevEx](https://umesh-malik.com/blog/tag/devex)[Codex](https://umesh-malik.com/blog/tag/codex)[GenAI](https://umesh-malik.com/blog/tag/genai)[Axios](https://umesh-malik.com/blog/tag/axios)[GPT-5](https://umesh-malik.com/blog/tag/gpt-5)[China](https://umesh-malik.com/blog/tag/china)[Tools](https://umesh-malik.com/blog/tag/tools)[Rust](https://umesh-malik.com/blog/tag/rust)[vLLM](https://umesh-malik.com/blog/tag/vllm)[CUPS](https://umesh-malik.com/blog/tag/cups)[LLVM](https://umesh-malik.com/blog/tag/llvm)[eBPF](https://umesh-malik.com/blog/tag/ebpf)[Qwen](https://umesh-malik.com/blog/tag/qwen)[x402](https://umesh-malik.com/blog/tag/x402)[LLMs](https://umesh-malik.com/blog/tag/llms)[HTML](https://umesh-malik.com/blog/tag/html)[HTTP](https://umesh-malik.com/blog/tag/http)[DMCA](https://umesh-malik.com/blog/tag/dmca)[Math](https://umesh-malik.com/blog/tag/math)[NIST](https://umesh-malik.com/blog/tag/nist)[Vite](https://umesh-malik.com/blog/tag/vite)[API](https://umesh-malik.com/blog/tag/api)[SDK](https://umesh-malik.com/blog/tag/sdk)[TLS](https://umesh-malik.com/blog/tag/tls)[GPU](https://umesh-malik.com/blog/tag/gpu)[GEO](https://umesh-malik.com/blog/tag/geo)[SEO](https://umesh-malik.com/blog/tag/seo)[MCP](https://umesh-malik.com/blog/tag/mcp)[LSP](https://umesh-malik.com/blog/tag/lsp)[CLI](https://umesh-malik.com/blog/tag/cli)[DNS](https://umesh-malik.com/blog/tag/dns)[SVG](https://umesh-malik.com/blog/tag/svg)[SRE](https://umesh-malik.com/blog/tag/sre)[LLM](https://umesh-malik.com/blog/tag/llm)[RAG](https://umesh-malik.com/blog/tag/rag)[SPA](https://umesh-malik.com/blog/tag/spa)[AWS](https://umesh-malik.com/blog/tag/aws)[HLS](https://umesh-malik.com/blog/tag/hls)[npm](https://umesh-malik.com/blog/tag/npm)[GTC](https://umesh-malik.com/blog/tag/gtc)[CSS](https://umesh-malik.com/blog/tag/css)[AI](https://umesh-malik.com/blog/tag/ai)[V8](https://umesh-malik.com/blog/tag/v8)