Running LLMs Locally: Gemma, Ollama, and Practical Choices
How to decide between local and cloud, where Gemma fits, which runtime to pick, and what hardware you actually need for useful local AI.
Posts
Articles
Technical notes, experiments, and field reports on AI agents, coding tools, security failures, and verification workflows from real production use.
Exa Search: The AI-Native Search Engine Built for Agents
Deep dive into Exa, the AI-native search API. Real benchmarks: 452ms latency, 79-90% token savings, semantic discovery vs keyword matching.
Claude Code Leak: The Hidden Features That Escaped, and What Builders Should Actually Care About
The Claude Code leak exposed hidden features, but the deeper lesson is operational: package artifacts can leak product boundaries, internal experiments, and roadmap intent.
AI Tools in March 2026
March 2026 AI tool recommendations by budget tier — free options, $20/mo, under $100, and $200+. Updated for the current free tier landscape.
Migrating from OpenAI to Kimi, Claude, or Antigravity (2026)
Complete migration guide: export your OpenAI data, compare features with Kimi k2.5 and Claude, cut costs by 80%.
OpenClaw Provider Policy Check 2026: Complete Guide
Find out if your AI provider allows OpenClaw usage. 10-second status check for Anthropic, Google, OpenAI, Kimi, and 10+ providers with migration paths if you're at risk.
Google Lyria Music: Current Access and February Field Notes
Choose Lyria 3.5 in Gemini, Flow Music or the paid API. Hear eight historical Lyria 3 audio clips and check prompts, download limits and privacy.
Anthropic Blacklisted by Pentagon: What Happened
Anthropic was formally designated a 'supply chain risk' and blacklisted from all U.S. government work on February 27 — hours before OpenAI announced a Pentagon deal containing the same safety redlines Anthropic was punished for holding.
Google Whisk first look: subject-scene-style video generation (experimental)
Hands-on with Google Whisk: a three-ingredient approach to AI video generation — subject, scene, style — with 3 free generations and surprising results when you guide it well.
OpenCode GLM-5 Free Tier Snapshot
Historical snapshot of OpenCode's GLM-5 free-tier moment, updated to point readers toward GLM-5.1 and avoid stale leaderboard claims.
Google Flow and Veo: Credits, Controls and a Video Workflow
Choose a Google Flow model, understand video credits and privacy, and follow a reference-led shot workflow. Includes five historical February Veo generations.
Anthropic OAuth Policy Feb 2026: What Changed
Anthropic's official Claude Code compliance docs explicitly prohibit OAuth tokens in third-party tools, including the Agent SDK. Here's what's new, why OpenCode broke, and where the OSS ecosystem goes next.
UltraThink → UltraQuiet: Why Devs Want Receipts
Claude Code started hiding file paths and search details behind Ctrl+O. Here's a working fix: the AGENTS.md Audit Ledger pattern.
Claude Opus 4.6 Extra Use: $50 Free Credits (Ends Feb 16)
Urgent: Anthropic is giving away $50 in free Opus 4.6 credits until Feb 16. Plus how to save 50% with batch processing for non-urgent workloads.
From Phone to Live Site in 10 Minutes: Kimi's Website Builder
How to generate production landing pages entirely from mobile using Kimi k2.5's website builder agent. Complete workflow with prompt templates and live demo.
The 20-Minute Blog: A Provenance-Corrected History
An annotated recovery of AIHackers' 2023 publishing test: ChatGPT and Midjourney supported a ZimmWriter draft made with text-davinci-003.
AGENTS.md: What Actually Works (And What Doesn't)
Guide to writing AGENTS.md files, drawing on production usage and vendor documentation, with an October 2026 correction to an unverified Vercel attribution.
AIHackers Vibe Coding History: 2023 Archive Review
A source-labeled history of five legacy AIHackers routes: four recovered 2023 bodies, one unresolved page, and what the artifacts support.
Codex vs Claude Code vs Kimi k2.5: Three Paradigms for AI-Assisted Development
A comparative analysis of three AI coding approaches: OpenAI Codex's parallel cloud agents, Claude Code's terminal-native transparency, and Kimi k2.5's open ecosystem with 100 sub-agent swarms.
Kimi K2.5's Open-Source Pricing Strategy: How Moonshot AI Is Buying Market Share
Strategic analysis of Moonshot AI's playbook: open weights + aggressive promotional pricing ($0.99 first month via AI agent) to capture developers from closed-source incumbents. Includes agent swarm impressiveness framework and market positioning vs Codex/Claude.