Pete Shaw
ptshaw.bsky.social
Pete Shaw
@ptshaw.bsky.social
Research Scientist at Google DeepMind. Mostly work on ML, NLP, and BioML. Based in Seattle.

http://ptshaw.com
Excited to share a new paper that aims to narrow the conceptual gap between the idealized notion of Kolmogorov complexity and practical complexity measures for neural networks.
October 1, 2025 at 2:11 PM
Reposted by Pete Shaw
Excited to share 𝐈𝐧𝐟𝐀𝐥𝐢𝐠𝐧!

Alignment optimization objective implicitly assumes 𝘴𝘢𝘮𝘱𝘭𝘪𝘯𝘨 from the resulting aligned model. But we are increasingly using different and sometimes sophisticated inference-time compute algorithms.

How to resolve this discrepancy?🧵
January 1, 2025 at 7:59 PM
I'll be at NeurIPS this week. Please reach out if you would like to chat!
December 9, 2024 at 9:51 PM
Reposted by Pete Shaw
New starter pack! go.bsky.app/GZ4hZzu
October 28, 2024 at 9:43 AM
Reposted by Pete Shaw
Two BioML starter packs now:

Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc

DM if you want to be included (or nominate people who should be!)
I tried to make a bioml starter pack. DM if you want me to add or remove you?

go.bsky.app/2VWBcCd
Anybody have a bioml starter pack?
November 18, 2024 at 5:09 PM
Reposted by Pete Shaw
Wanted to share that Varun Godbole recently released a prompting playbook. The title says prompt tuning, but this is text prompts, not soft prompts.

github.com/varungodbole...
GitHub - varungodbole/prompt-tuning-playbook: A playbook for effectively prompting post-trained LLMs
A playbook for effectively prompting post-trained LLMs - varungodbole/prompt-tuning-playbook
github.com
November 11, 2024 at 3:51 PM
Reposted by Pete Shaw
New here? Interested in AI/ML? Check out these great starter packs!

AI: go.bsky.app/SipA7it
RL: go.bsky.app/3WPHcHg
Women in AI: go.bsky.app/LaGDpqg
NLP: go.bsky.app/SngwGeS
AI and news: go.bsky.app/5sFqVNS

You can also search all starter packs here: blueskydirectory.com/starter-pack...
November 9, 2024 at 9:13 AM
Getting set up on Bluesky today!
November 16, 2024 at 12:40 AM
Reposted by Pete Shaw
I’m pretty excited about this one!

ALTA is A Language for Transformer Analysis.

Because ALTA programs can be compiled to transformer weights, it provides constructive proofs of transformer expressivity. It also offers new analytic tools for *learnability*.

arxiv.org/abs/2410.18077
ALTA: Compiler-Based Analysis of Transformers
We propose a new programming language called ALTA and a compiler that can map ALTA programs to Transformer weights. ALTA is inspired by RASP, a language proposed by Weiss et al. (2021), and Tracr (Lin...
arxiv.org
October 24, 2024 at 3:31 AM