HackerTrans
TopNewTrendsCommentsPastAskShowJobs

snats

no profile record

Submissions

Show HN: Ranking every disease (the unmet needs index)

insights.convoke.bio
4 points·by snats·قبل شهرين·0 comments

Erebor: New bank by Palmer Luck [pdf]

occ.gov
2 points·by snats·قبل 5 أشهر·1 comments

Famous Disease

weblog.snats.xyz
2 points·by snats·قبل 5 أشهر·0 comments

Famous Disease

weblog.snats.xyz
3 points·by snats·قبل 7 أشهر·0 comments

Famous Disease

weblog.snats.xyz
2 points·by snats·قبل 7 أشهر·1 comments

Flow-Lenia: Towards open-ended evolution in cellular automata

arxiv.org
4 points·by snats·قبل 7 أشهر·0 comments

Machines of Entretainment

weblog.snats.xyz
1 points·by snats·قبل 10 أشهر·0 comments

comments

snats
·قبل شهرين·discuss
did a pretty similar thing last month for the text rendering library last month.

trained and made a viz for the model and then made it displace text.

should probably do a proper write-up:https://x.com/i/status/2038367016969724259
snats
·قبل 4 أشهر·discuss
you can also have removed layers of models and keep the same score in benchmarks [1].

i feel that sometimes a lot of the layers might just be redundant and are not fully needed once a model is trained.

[1] https://snats.xyz/pages/articles/pruningg.html
snats
·قبل 6 أشهر·discuss
personal website: snats.xyz weblog: weblog.snats.xyz
snats
·قبل 10 أشهر·discuss
I also did a couple of experiments with pruning LLMs[1] using genetic algorithms and you can just keep removing a surprising amount of layers in big models before they start to have a stroke.

[1]https://snats.xyz/pages/articles/pruningg.html