sankalp
@dejavucoder
LLMs and shitposting into crafting ai products and evals dm open to talk on ai engg/post-training
قد يعجبك
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…
i can confirm. should we add this task to karpathy bench?
i am once again saying. you do not understand automation as well as I do.
how do you explain this? is it bots? or the people are the bots or both? algo pushed to people who usually like these threads? only 2 RTs (one from sub 1k, one from 8k follower account)
You’re in a Member of Technical Staff interview at Anthropic, and the interviewer (amanda askell) asks: “what's the difference between dry claude and wet claude" here's how you will answer 👇
cuda lovers you gonna love this
PMPP-Eval is live, together with pmpp env and dataset, Releasing "Programming Massively Parallel Processors" book turned into environment that lets your LLM practice over QA/Coding exercises. Touched the whole process of going from a book to a optimized CUDA env over on blog.
Announcing Bread Technologies. We’re building machines that learn like humans. We raised a $5 million seed round led by Menlo Ventures and have been building in stealth for 10 months. Today, we rise 🍞
You’re in a Member of Technical Staff interview at Anthropic, and the interviewer (amanda askell) asks: “what's the difference between dry claude and wet claude" here's how you will answer 👇
this interview question would filter out 99.9% of candidates: “what’s the difference between dry claude and wet claude?"
reinforcement learning be like oh my tea is not good, maybe the reason is i woke up on the wrong side of the bed today and then karpathy says its worse but everything we have had before it was worse and i am like understandable sir have a nice day
ml people not using deep learning jargon in their jokes challenge (impossible)
pretty interesting that both codex and claude code do not stream outputs. both show some state as to what the models are doing but none of the tokens are "streamed". you recieve all the output at once.
United States الاتجاهات
- 1. Good Tuesday 27.1K posts
- 2. White House 352K posts
- 3. Cobie 40.2K posts
- 4. #tuesdayvibe 1,662 posts
- 5. NBA IS BACK 11.8K posts
- 6. Happy NBA 5,772 posts
- 7. Sanae Takaichi 79.1K posts
- 8. East Wing 82.9K posts
- 9. WE ARE PROUD OF TAEHYUNG 35.5K posts
- 10. Texans 40.2K posts
- 11. #TuesdayMotivation N/A
- 12. #Wordle1585 N/A
- 13. #Talus_Labs N/A
- 14. Gucci 27.6K posts
- 15. Sliwa 47.7K posts
- 16. Curtis 42K posts
- 17. #ThunderUp N/A
- 18. Blue Jays 105K posts
- 19. WE LOVE YOU TAEHYUNG 40.8K posts
- 20. Pizza Hut 7,712 posts
قد يعجبك
-
vijay singh
@dprophecyguy -
TDM (e/λ) (L8 vibe coder 💫)
@cto_junior -
sandrone
@kosenjuu -
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.