Cody Blakeney
@code_star
Data Dawg @datologyai | Formerly Data Research Lead @DbrxMosaicAI | Visiting Researcher @ Facebook | Ph.D | #TXSTFOOTBALL fan | http://linktr.ee/code_star
Bạn có thể thích
We are looking for a post-training lead at @datologyai we have gpus, you can make them go brrrr
Me eating my hot Cheetos: “I told you that huel shit was bad for you”
not possible for someone to be more personally victimized by a song than I am by this one spotify.link/zSzDpYoUuXb
i think about this everyday
when you're the eval guy and you check up on the experiments channel in slack
looking at data is like eating lava. it warms me up inside but kills me
Accidentally said « AdamW » instead of « muon » and they kicked me out of SF
Accidentally said "looks good" instead of "SOTA" and they kicked me out of SF
GPU computing before CUDA was *weird*. Memory primitives were graphics shaped, not computer science shaped. Want to do math on an array? Store it as an RGBA texture. Fragment Shader for processing. *Paint* the result in a big rectangle.
Accidentally said “orthogonal” instead of “opposite” in florida and desantis is shipping me back to SF
Accidentally said "hard" instead of "non-trivial" and they kicked me out of SF
banger
looking at data is like eating lava. it warms me up inside but kills me
Unbelievably good hire for @AnthropicAI . Excited to see what y'all cook up!
Excited to announce that @dsmilkov and I have joined @AnthropicAI to work on tooling for mechanistic interpretability research 🐜 🐜 If you have worked with me you know I’ve been obsessed with Claude and now we will be opening it up to understand what’s going on inside, and help…
When I have multiple Anneals and some CPT runs
not your weights not your model not your mind
Am I wrong in sensing a paradigm shift in AI? Feels like we’re moving from a world obsessed with generalist LLM APIs to one where more and more companies are training, optimizing, and running their own models built on open source (especially smaller, specialized ones) Some…
Give it a year or two and we will have nanoagent. Then nanoagent speed run. Then nanoASI and so on.
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,…
Still thinking about this banger
when you're the eval guy and you check up on the experiments channel in slack
HAHAHAHAHAHA IT'S A VIDEO FROM THE PORT OF LONG BEACH CALIFORNIA 🇺🇸🇺🇸🇺🇸🇺🇸🇺🇸
Here’s a scaling law that matters more: every two years the gap to frontier closes by a factor of 2x
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,…
United States Xu hướng
- 1. Gabe Vincent 3,046 posts
- 2. #AEWDynamite 17.2K posts
- 3. #VSFashionShow 518K posts
- 4. Angel Reese 45.3K posts
- 5. Deport Harry Sisson 5,436 posts
- 6. #Survivor49 3,251 posts
- 7. #youtubedown 15.9K posts
- 8. tzuyu 208K posts
- 9. #stlblues 1,634 posts
- 10. Quen 28.8K posts
- 11. George Kirby 2,275 posts
- 12. Darby 4,930 posts
- 13. jihyo 167K posts
- 14. Suarez 17.5K posts
- 15. Hofer 1,678 posts
- 16. Birdman 4,644 posts
- 17. Nazar 6,117 posts
- 18. Victoria's Secret 505K posts
- 19. Nancy 143K posts
- 20. Tusky 1,946 posts
Bạn có thể thích
-
Abhi Venigalla
@ml_hardware -
Tri Dao
@tri_dao -
Jonathan Frankle
@jefrankle -
Sam Havens
@sam_havens -
Jan Leike
@janleike -
Matthew Leavitt
@leavittron -
Sharon Y. Li
@SharonYixuanLi -
Ofir Press
@OfirPress -
Vitaliy Chiley
@vitaliychiley -
Mihir Patel
@mvpatel2000 -
Michael Carbin
@mcarbin -
Tom Goldstein
@tomgoldsteincs -
labml.ai
@labmlai -
Mostafa Dehghani
@m__dehghani -
rohan anil
@_arohan_
Something went wrong.
Something went wrong.