Measured

I've run tmux since somewhere in 2016 because I can script it. Ten years of scripts later my status bar was using 15.4% of a core on battery, so I measured it, cut it to one call, and moved the scripts into one Rust binary.

The first independent framework for measuring political bias in large language models. Chinese models cluster at one pole, and bias grows as models scale.

In July a Show HN produced a working bypass and two people saying signature matching was the wrong method. They were right. What the rule layer actually catches on real attacks (19.8%), why 59% of the misses cannot be caught by any input filter, a provena

Measured runs on rented GPUs: what each provider actually charged, and the cost per finished unit of work.

A fixed corpus of diary scenarios, run on real hardware against every iOS 27 beta and the release candidate, scored before and after a deterministic repair layer. Real numbers: what Apple fixed, what

8 clicks or 54: what four spec-driven tools actually cost before you write a line of code

A case went from 5/5 to 2/5 with nothing changed. How I measured the noise floor of an LLM-judged eval, what it caught the week after, and where it still can

We watched almost 17k sessions across different types of personas, with 1,163 prompt variations, 75 repositories and 3 coding agents (Claude Code, Codex, Cursor) actually implementing the solutions instead of just recommending one.

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