내가 좋아할 만한 콘텐츠
you can read my latest blogpost: my experience with claude code after 2 weeks of adventure now - some lore why i started using it - it's several features - my current workflow - must know commands almost like a beginner guide or log if you will sankalp.bearblog.dev/my-claude-code…
was in e/xperiments discord office hours with @tokenbender recently and he was advocating that we should seed the models with our own raw thoughts and build upon it - LLMs as augmentators. instead of outsourcing thinking and idea gen, be steve jobs and let llm be the wozniak.
steve jobs was the prompter, and woz, his llm the bitter engineers coming out of the woodwork to criticize llms are coming to the realization that no matter how good they were, they were ultimately replaceable this whole time but no tech is coming to replace jobs
i swear this feature is playing with me. i never see will brown's post. 50% of the times i would see the 2nd and 3rd person's posts.
people are still figuring out things about codex sydney sweeney and me have been saying since 1 month now...
model be like:
We're doing all kinds of stuff with these models that the public isn't even thinking of yet.
one of the most interesting evals or attempts to test shape rotating powers of a language model i have seen in a while. so simple yet challenging the models in latent space.
can your llm rotate a shape inside it's head? i found out yes but it's a fucking idiot when it comes to the upper layer... why? non uniform spatial reasoning.... here's an eval to test the internal latent reasoning of your models.
love karpathy sensei's koding koding koding energy
Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single,…
read this thread an year ago but i didn't fully understand it today lol. cursor codebase indexing is clever in the sense they separate the semantic search (cloud) from actual code access (done locally). they store your codebase embeddings on cloud with reference meta-data. they…
An underrated part of Cursor is our codebase indexing system. It provides efficient indexing/updating without storing any code on our servers. (1/9)
Introducing nanosft, a clean single file implementation of finetuning for chat style model. Loads gpt2-124M weights on nanogpt and does supervised finetuning using just pytorch. a side project that I made recently for some prep. link below :) qts/rts appericiated
the 'you're absolutely right' problem is similar or worse with sonnet 4.5 and more than annoyance, i find it hard to trust the output when the model says so especially for more subjective tasks
asked a difficult technical question to a friend who got claude merch recently and he said wait a second... let me put on my thinking cap first
United States 트렌드
- 1. Happy Birthday Charlie 47.6K posts
- 2. Good Tuesday 30.5K posts
- 3. #tuesdayvibe 3,276 posts
- 4. Shilo 1,266 posts
- 5. #NationalDessertDay N/A
- 6. Pentagon 74.1K posts
- 7. #PutThatInYourPipe N/A
- 8. #Worlds2025 42.5K posts
- 9. #TacoTuesday N/A
- 10. Victory Tuesday N/A
- 11. Standard Time 2,948 posts
- 12. Dissidia 6,334 posts
- 13. Happy Birthday in Heaven 1,373 posts
- 14. Martin Sheen 6,415 posts
- 15. Janet Mills 1,494 posts
- 16. No American 63.8K posts
- 17. Presidential Medal of Freedom 28.9K posts
- 18. JPMorgan 12.2K posts
- 19. Time Magazine 17.6K posts
- 20. Windows 10 22.1K posts
내가 좋아할 만한 콘텐츠
-
vijay singh
@dprophecyguy -
TDM (e/λ) (L8 vibe coder 💫)
@cto_junior -
sandrone
@sand7one -
shrihacker
@shrihacker -
shaurya
@shauseth -
fudge
@fuckpoasting -
🎙️Ankush Dharkar ☯️
@ankushdharkar -
Indro
@IndraAdhikary7 -
filterpapi
@filterpapi -
gravito
@Gravito841 -
pragun
@pragdua -
Out Of Office⭕
@Parikshit_K_ -
OTAKU
@OtakuProcess -
Nirant
@NirantK -
ankit
@ankitiscracked
Something went wrong.
Something went wrong.