Kev is three models, at 0.8B, 4B and 9B, each a rank-16 LoRA adapter and a pointer head on a Qwen3.5 base. You hand it a piece of text and a set of yes/no, multiple-choice or rating questions, and it returns probabilities rather than a…
In the News: September 21, 2026 (Morning)
A local decision model ships with published calibration numbers and a frozen eval you can rerun, so a verification loop can be audited rather than trusted.
Morning edition
Machine-readable
Download Markdown
Story
A decision model that publishes where it is wrong
Read story →
Story
Draw the map before the agents start
Osmani's premise is that in an old system "the repository is no longer a complete description of how the thing actually behaves", and that agents make a change cheap to attempt without making it cheap to verify. His answer is to zone the…
OpenSpec
The spec framework's front page names a five-stage loop, /opsx:explore, /opsx:propose, /opsx:apply, /opsx:verify and /opsx:archive, with verify defined as checking that the implementation matches the spec. Fission claims 69,700 GitHub stars and more than 265,000 developers a month, and lists compatibility with 39 coding agents including Claude Code, Codex, Cursor, Copilot, Gemini CLI and opencode. Those figures are the vendor's own and the page is a product page. The part worth noting is the shape: a named verification stage being distributed as a cross-harness convention rather than written once per team.
In September, AI generated code has made up 17.25% of all Linux Kernel patches
No primary has been read for this one, the submission points at a post on X by the Lunduke Journal, and neither the percentage nor the method behind it is reported here as established. What is reportable is the argument: 27 points against 52 comments at 07:09 EDT, a ratio that usually marks a contested claim rather than an endorsed one. The question underneath it, what share of accepted upstream work in a large open-source project is now agent-written, is one almost nobody has a measured answer to.