Kevin Patrick Murphy
@sirbayes
Research Scientist at Google DeepMind. Interested in Bayesian Machine Learning.
You might like
This is a much more intuitive version of the prisoners dilemma from Jon Kleinberg’s excellent book, cs.cornell.edu/home/kleinber/…, that covers the holy trifecta that Michael Jordan keeps discussing, namely Econ + CS + stats. (Very relevant for a future with human and AI agents …)
Maybe thinking machines should be renamed LoRaS - Lora as a service? ;) this seems to be their business model, at least for now. Since training is cheap, a whole ecosystem of specialized models will bloom, and they can charge for serving them all in parallel. Smart.
I am pleased to share our new NeurIPS paper for online Bayesian inference for neural networks. Instead of focusing on updating the parameter posterior, we work with the predictive posterior (which makes much more sense for non-identifiable models, and gives us more algorithmic…
Our paper “Martingale Posterior Neural Networks for Fast Sequential Decision Making” has been accepted at #neurips2025! Joint work with @l_sbetancourt, @AlvaroCartea and @sirbayes Blog: grdm.io/posts/bnn-with… Paper: arxiv.org/abs/2506.11898 Code: github.com/gerdm/martinga…
Hi @karpathy . I loved your interview! However, you said there is no work on LLM self-play. Not true. See eg "Spiral" from @natashajaques et al (agent-v-agent) and "Absolute Zero Reasoner" from @_AndrewZhao et al. (agent-v-env). Probably others.
My pleasure to come on Dwarkesh last week, I thought the questions and conversation were really good. I re-watched the pod just now too. First of all, yes I know, and I'm sorry that I speak so fast :). It's to my detriment because sometimes my speaking thread out-executes my…
Good article on AI / data center boom / bubble. The costs will outweigh returns for many years, until we make models much more efficient to train and serve (thinking tokens, I’m looking at you), and we reduce energy costs, and the tech becomes reliable enough to be integrated…
beautiful work on (self) distilling diffusion / flow models!
We've cleaned up the story big time on flow maps. Check out @nmboffi's slick repo implementing all the many ways to go about them, and stay tuned for a bigger release 🤠 arxiv.org/pdf/2505.18825 flow-maps.github.io
Bob Carpenter, who is the main dev for @mcmc_stan, finally gets "Jax-pilled" :) statmodeling.stat.columbia.edu/2025/10/03/its… With cheap (even free) GPUs on Google Colab and Lightning AI studio, it is now easy to get 10x-100x speedups for HMC, and more if you switch to SVI.
I agree with @karpathy 's take here. The interview between @RichardSSutton and @dwarkesh_sp was interesting, but I think at times there was a communication gap due to some misunderstandings. I would say that the current LLM training setup is very similar to the classic…
Finally had a chance to listen through this pod with Sutton, which was interesting and amusing. As background, Sutton's "The Bitter Lesson" has become a bit of biblical text in frontier LLM circles. Researchers routinely talk about and ask whether this or that approach or idea…
United States Trends
- 1. Happy Thanksgiving 488K posts
- 2. Turkey Day 22.6K posts
- 3. #Thankful 5,910 posts
- 4. #Gratitude 5,776 posts
- 5. Afghanistan 209K posts
- 6. #Grateful 3,276 posts
- 7. Feliz Día de Acción de Gracias 1,548 posts
- 8. #StrangerThings5 376K posts
- 9. #DareYouToDeath 336K posts
- 10. Good Thursday 25.3K posts
- 11. Jonathan Groff N/A
- 12. DYTD TRAILER 255K posts
- 13. Taliban 55.7K posts
- 14. Gobble Gobble 17.3K posts
- 15. Al Roker N/A
- 16. Hoda 2,166 posts
- 17. God for His 19.8K posts
- 18. The CIA 163K posts
- 19. Piers 23.2K posts
- 20. Asylum 155K posts
You might like
-
Jürgen Schmidhuber
@SchmidhuberAI -
Yi Ma
@YiMaTweets -
Soumith Chintala
@soumithchintala -
Peyman Milanfar
@docmilanfar -
Michael Black
@Michael_J_Black -
Percy Liang
@percyliang -
Aran Komatsuzaki
@arankomatsuzaki -
Zoubin Ghahramani
@ZoubinGhahrama1 -
Max Welling
@wellingmax -
Lucas Beyer (bl16)
@giffmana -
Sasha Rush
@srush_nlp -
Petar Veličković
@PetarV_93 -
Christopher Manning
@chrmanning -
Yannic Kilcher 🇸🇨
@ykilcher -
Jia-Bin Huang
@jbhuang0604
Something went wrong.
Something went wrong.