Post

Put up a new Iterative Refinement episode. First public demo of PEAK, a tool that extracts the unwritten rules from codebases and tests whether contributors actually understand what they shipped. youtu.be/O1iBjGT9lRI?...

The core research (first shown at @qconferences.com London): every repo has rules nobody documented. You only know them because you've been there for years. We pull them out computationally from commit history. PEAK turns them into questions. #opensource #airesearch

Walked through real PRs across @scikit-learn.org, @openclaw-x.bsky.social, @scipyconf.bsky.social, #crewAI and @opensource.block.xyz .

PEAK asks totally different things depending on the repo. The #scipy questions about FITPACK and rank deficiency are a world apart from the #openclaw questions about session state architecture.

The @opensource.block.xyz PR is maybe my favorite. @Jack Dorsey is the author. The agent picked "approximately 4 characters per token" as a cost heuristic and capped model memory at 20. Gets into authority in code review. #vibecoding

Lots of knock-on consequences: PR review as cargo culting. Clean-room reimplementation to license wash and take over control. People are ready to wildly change the rules of the SDLC within and beyond #OSS.

Still, there's such a thing as consequential computing. Code that touches money, health, human life. Someone still needs to have climbed the mountain and developed the expertise.

The SWE role is getting harder *and* more interesting. The days of body shops are over. This is rapidly becoming a job for people who can legit bring a huge amount of leverage, because we just don't need to push a bunch of boiler plate around with human hands.