Viewing profile — mvyshnyvetska

[dead]

LLMs forget. The standard fix is RAG — retrieve chunks, stuff them in. It works until it doesn't: irrelevant chunks waste tokens, summaries lose structure, and nothing actually mod…

Yeah, that's more process-tooling territory — keeping this dev-focused for now.

Update: just shipped --brief flag. Thanks for the push!

Fair points :). The naming is 'evolutionary' — started as 'semantic diff' because it analyzes meaning not just lines, but 'commit review' is more accurate for what it does now. You…

Hi HN — I built semantic-diff for myself, and it turned out surprisingly useful. Regular git diff shows what changed. semantic-diff tries to answer: – why was this change made? – w…

Interesting approach. A few questions: How do you handle false positives from mutation strategies like Base64 or token smuggling? In my experience, a lot of "successful" jailbreaks…

Anthropic's recent piece on effective harnesses for long-running agents hit close to home. We've been wrestling with the same problems — agents that try to one-shot everything, dec…

Hit exactly this problem some time ago (preliminarily buried 5 or 6 versions of memory systems). Generic summaries or RAG results often feel useless because models optimize for "wh…

We've been solving similar problems differently. Instead of a flat progress.txt, we use three layers: semantic context (what are we building and why), structured intention tracking…