Hacker News: andawaywego

New comment by andawaywego in "NY announces game ownership bill requiring ownership rather than licensing"

andawaywego — Mon, 19 Oct 2026 05:17:51 +0000

the adobe suite clones are vibe coded clean room implementations, decompiles on the other hand should compile 1:1 to the existing software, and we have ways to verify that's the case. recompiles from my understanding of the term are somewhere inbetween.

New comment by andawaywego in "How to stop Claude from saying load-bearing"

andawaywego — Wed, 15 Jul 2026 11:05:58 +0000

something akin to degrees of separation from the source, considering people have been complaining about this when it was "here's an explanation from google/wikipedia/stackoverflow" long before llms

New comment by andawaywego in "The git history command"

andawaywego — Tue, 14 Jul 2026 14:15:22 +0000

plenty of models do fine with assuming a flat earth. git is an incredibly competent swiss army knife for building VCS but I'm not convinced it's the best we can ever do (nor we have ever done) for the simple linear history we expect from your usual corpo crud.

New comment by andawaywego in "The git history command"

andawaywego — Tue, 14 Jul 2026 14:08:12 +0000

can you elaborate what concrete value you've managed to extract from doing things like this? my gut reaction is that any benefit would be overshadowed by multiplying effort for other team members to catch up on their work, and if it makes it harder to work when even one person does it I can't imagine it scaling on a full team (or worse, something like a monorepo)

New comment by andawaywego in "Can AI Pass Freshman CS? [video]"

andawaywego — Wed, 21 Jan 2026 12:28:39 +0000

Main issues I could find through skimming is conflating chat performance (sometimes very clearly tool-less) with agent performance, not allowing the AI to self organize on a cross-video consistent repo, not providing any persisted feedback, and a little nitpickedly going through providing motivating material in such a weird and inconsistent way sometimes with links instead of downloaded files and such.

In some cases even for the agent examples I just have to assume that the AI encountered some issue applying tooling and was forced to run in text mode throughout? Unfortunately there seems to be so much missing context for the viewer of what the assignment, process, expected and resulting output are that you can only really guess at what's going on from the most outwardly bewildering (to the OP) behaviour.