Thompson scores his team's harness against the twelve theses in Ryan Lopopolo's harness-engineering repository, the follow-up to OpenAI's February post on shipping with Codex. He reports that on a legacy codebase with the harness switched…
In the News: October 17, 2026 (Morning)
Orbital Witness's CTO reports merged PRs per engineer roughly doubled after a harness rebuild, and grades the team against OpenAI's twelve theses.
Morning edition
Machine-readable
Download Markdown
Story
Orbital Witness reports merged PRs per engineer roughly doubled after a harness rebuild, and marks three of twelve theses as half-built
Read story →
DeepSeek-V4.1-Flash-1017
Hugging Face model card · MIT-licensed open weights with a 1M-token context window. DeepSeek reports 42.3 on Terminal-Bench 4.0 using the Claude Code harness, up from 31.2 for the previous Flash release. These are the vendor's own figures, not independently reproduced.