noahdgoodman
@noahdgoodman
Followers
5K
Following
365
Media
8
Statuses
260
Professor of natural and artificial intelligence @Stanford. Alignment at @GoogleDeepMind. (@StanfordNLP @StanfordAILab etc)
Joined November 2019
So proud! . Go work with Gabriel, he’ll be the best advisor.
Thrilled to join the UMich faculty in 2026!. I'll also be recruiting PhD students this upcoming cycle. If you're interested in AI and formal reasoning, consider applying!.
0
5
30
RT @sydneymlevine: 🔥 New position piece! 🔥 In this paper we lay out our vision for AI Alignment as guided by "Resource Rational Contractual….
0
21
0
It’s like chain-of-thought for humans!.
Can we record and study human chains of thought? .The think-aloud method, where participants voice their thoughts as they solve a task, offers a way! In our #CogSci2025 paper co-led with Ben Prystawski, we introduce a method to automate analysis of human reasoning traces! (1/8)🧵
0
4
13
It turns out that a lot of the most interesting behavior of LLMs can be explained without knowing anything about architecture or learning algorithms. Here we predict the rise (and fall) of in-context learning using hierarchical Bayesian methods.
🚨New paper! We know models learn distinct in-context learning strategies, but *why*? Why generalize instead of memorize to lower loss? And why is generalization transient?. Our work explains this & *predicts Transformer behavior throughout training* without its weights! 🧵. 1/
4
20
111
RT @rohinmshah: Just released GDM’s 100+ page approach to AGI safety & security! (Don’t worry, there’s a 10 page summary.). AGI will be tra….
0
71
0
RT @ma_tay_: 🤔🤖Most AI systems assume there’s just one right answer—but many tasks have reasonable disagreement. How can we better model hu….
0
37
0
RT @mcxfrank: AI models are fascinating, impressive, and sometimes problematic. But what can they tell us about the human mind?. In a new r….
0
41
0
“Four habits of highly effective STaRs” — we show that certain high level cognitive behaviors are necessary for learning to reason through RL. Exciting!.
New Paper!! We try to understand why some LMs self-improve their reasoning while others hit a wall. The key? Cognitive behaviors! Read our paper on how the right cognitive behaviors can make all the difference in a model's ability to improve with RL! 🧵1/13
0
5
41
This may be a deep failure of understanding or a shallow result of current alignment goals. But it is striking to see in a world where language models *get everything right".
1
0
7
In new work we compared explored behavior of large language models on the same task. We found models were very poor at understanding hyperbole, and even reversed patterns in human data for halo effects.
1
0
5
In 2014 Kao, Wu, Bergen, and I studied number word interpretation, such as:."That latte cost a million dollars" vs "That latte cost three dollars". (hyperbole)."I'll meet you at 11:57a" vs "I'll meet you at noon". (halo).
1
0
6
A note on hyperbole, halo, and language models. No not about startup valuations!.
1
3
12
RT @elicitorg: We raised a $22M Series A and are launching Elicit Reports, a better version of Deep Research for actual researchers. Elici….
0
92
0
Congrats to OAI on producing a reasoning model! Their opaque tweets demonstrate that they’ve (independently) found some of the core ideas that we did on our way to STaR.
Congrats to DeepSeek on producing an o1-level reasoning model! Their research paper demonstrates that they’ve independently found some of the core ideas that we did on our way to o1.
29
129
2K
RT @jphilippfranken: Presenting this tomorrow at @NeurIPSConf East Exhibit Hall A-C #2111 (4:30 p.m. PST — 7:30 p.m. PST). Come along if yo….
0
5
0
RT @GabrielPoesia: If you're at NeurIPS, come tomorrow for the Oral+Poster on "Learning Formal Mathematics from Intrinsic Motivation"! Real….
0
19
0