Tag
Dan Shipper hosts a live stream where he vibe checks a new AI model.
A tweet reports that @hammer_mt has trained the flybrain system to perform vibe checks, indicating a development in AI or related technology.
A tweet from @reach_vb asking @simonw about methods to evaluate AI models or harnesses, referencing a saturated 'pelican on a bike svg' benchmark.
A reflection on current practices for verifying AI coding agent output, noting that developers often skim diffs and merge without fully auditing the agent's session activity, raising concerns about code review culture in the age of AI.