broski (@broskidotai) 's Twitter Profile
broski

@broskidotai

ai-ml

ID: 1601161501049376769

linkhttps://vipul-maheshwari.github.io/ calendar_today09-12-2022 10:27:55

224 Tweet

160 Takipçi

299 Takip Edilen

broski (@broskidotai) 's Twitter Profile Photo

rlms (recursive language models) are wild man, seriously! gave it a 3,000-line django queryset file. asked it to find every class, categorize methods, and identify design patterns. so it started by writing the python code to slice it into chunks, called itself 9 times on the

rlms (recursive language models) are wild man, seriously!

gave it a 3,000-line django queryset file. asked it to find every class, categorize methods,  and identify design patterns.

so it started by   writing the python code to slice it into chunks, called itself 9 times on the
broski (@broskidotai) 's Twitter Profile Photo

just shipped rlm (recursive language model) cli it's based on recursive language models paper (arXiv:2512.24601), so the layman logic is instead of stuffing your entire context into one llm call and hoping it doesn't go into context rot, rlm writes code to actually process the

just shipped rlm (recursive language model) cli

it's based on recursive language models paper (arXiv:2512.24601), so the layman logic is instead of stuffing your entire context into one llm call and hoping it doesn't go into context rot, rlm writes code to actually process the
broski (@broskidotai) 's Twitter Profile Photo

just shipped rlm (recursive language model) cli based on the rlm paper (arXiv:2512.24601) so the layman logic is instead of stuffing your entire context into one llm call and hoping it doesn't go into context rot, rlm writes code to actually process the data, slicing, chunking,

broski (@broskidotai) 's Twitter Profile Photo

help yourself fellas : github.com/viplismism/rlm… if you wanna add something or if you think something is missing, feel free to raise an issue

broski (@broskidotai) 's Twitter Profile Photo

the face you make when the founder says 'we're pivoting' for the 5th time this week and there's only 3 of you in the whole company?!

Ryo Lu (@ryolu_) 's Twitter Profile Photo

keep struggling when things come too easy, you don’t exercise the brain nor the emotions. ease can feel like progress, but it often skips the reps that actually change you. growth is usually a loop, not a straight line – you take passes. you try, you fail, you reframe. you come

Alex Zhang (@a1zhang) 's Twitter Profile Photo

I really want to like this paper as an exploration of how to refine an RLM (which I am very much in favor of), but IMO the conclusion is too short-horizon and sort of misses the argument of the original paper. tldr; the idea is to inject extra steps / self-reflection prompts to

broski (@broskidotai) 's Twitter Profile Photo

at this point of time i am just overwhelmed from the amount of new things coming up in ai, there is just too much to understand and keep up with the pace. i got 12 papers to read, 15 articles to skim and 3 projects running in parallel. how are you guys even keeping up with all