gkoreli.com

What happened when ChatGPT, Claude, Gemini, Grok, Perplexity, Copilot, Mistral, DuckDuckGo, Claude Code and Codex were asked to fetch a page on a live Cloudflare Worker: the User-Agent, Accept and Fetch Metadata headers received, vendor IP-list matches, o

Server-side visitor counts are inflated by browser-shaped automation, and the popular open-source tools do not catch it. Here is the ten-minute test that shows your gap, the two rules that close most of it without a script, what AI readership really looks

interp-engine, Neuronpedia's new interpretability engine, names 34 hook points once and compares 27 across engines. I audited the code and ran it on a Mac.

A code-backed guide to first-party blog analytics with Cloudflare Workers and D1: edge events, privacy, migrations, and public stats.

Bun 1.4 moves fifteen package jobs into one Rust-based binary. The package graph shrinks, but compatibility and maintenance move into the runtime.

Does llms.txt improve AI search? This live audit examines edge data, agent tools, Markdown, and GEO evidence-then shows what to build and measure.

Herdr gives coding agents durable terminal sessions, agent state, and a control API. Screen-derived semantics remain its limit.

The ghx AI-agent reconnaissance sidecar passed a 90-episode eval at 25 compression. My usage logs show a three-day burst, then silence.

AgentPort lets applications attach a user-owned AI agent with scoped grants, private transport, and no new model subscription per app.

Buzz gives agents signed accounts and shared local compute. Delegation reliability and private code access remain unfinished.