Posted live from a talk in Amsterdam covering "12-factor factories," SlopCodeBench, and something he called "the gas town situation"; 2,767 views and 24 likes about three hours after posting, with one reply confirming the talk took place. Only the announcement and corroborating reply were read; the talk itself was not located or watched.
In the News: September 18, 2026
A new study tests how planning, tool interfaces, and context management affect four coding models across 176 matched harness configurations.
Morning edition
Machine-readable
Download Markdown
Story
A controlled study tests planning, tools, and context management
The authors built a coding harness from scratch around a fixed ReAct execution loop, then varied three components independently: an explicit planning step, the action interface (a curated tool set versus a bash-only shell), and context…
Read story →