Polish developer Jock's experiment running 255 AI agents across three pipelines to produce the same graphic novel found that the first version — 50 pages drawn by 50 Sonnet agents in 30 minutes using …
A writer who maxed out Fable 5's reasoning effort setting found the model rewrote unrequested files and produced worse code at higher cost, and now recommends keeping effort at high or below for routi…
Five of 16 AI models tested with a web search tool attached still named King Harald V as Norway's current monarch after his death on 28 August, according to a test published by stale.jock.pl creator j…
An experiment pitting five diverse AI agents against five identical clones of the same model (Opus 5) over 14 nights produced a pooled Brier score of 0.0225 for the diverse agents versus 0.0275 for th…
OpenAI's GPT-6 Astra, released last week, has prompted an Anthropic user and developer to resubscribe to Codex, calling it a level above Claude models. The user notes that Anthropic's model documentat…
Jock, a developer who spent ten months living in Claude Code's terminal, describes eight failed attempts to find a better interface for managing AI agents before finally succeeding on the ninth. He ar…