iiinova — where your digital self keeps evolving

Noah Goodman

@noahdgoodman.bsky.social

3K followers 131 following 6 posts

Professor of Natural and Artificial Intelligence @Stanford. Safety and alignment @GoogleDeepMind.

Posts Replies Media

Reposted by Noah Goodman

Sydney Levine @sydneylevine.bsky.social · 25/06/2025

🔥 New position piece! 🔥 In this paper we lay out our vision for AI Alignment as guided by "Resource Rational Contractualism" (RRC). But wait -- what's that? A 🧵.

195

Reposted by Noah Goodman

Daniel Wurgaft @danielwurgaft.bsky.social · 28/06/2025

🚨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/

2527

Reposted by Noah Goodman

Daniel Wurgaft @danielwurgaft.bsky.social · 25/06/2025

Excited to share a new CogSci paper co-led with @benpry.bsky.social! Once a cornerstone for studying human reasoning, the think-aloud method declined in popularity as manual coding limited its scale. We introduce a method to automate analysis of verbal reports and scale think-aloud studies. (1/8)🧵

1288

Reposted by Noah Goodman

Taylor Sorensen @taylor-sorensen.bsky.social · 20/03/2025

🤔🤖Most AI systems assume there’s just one right answer—but many tasks have reasonable disagreement. How can we better model human variation? 🌍✨ We propose modeling at the individual-level using open-ended, textual value profiles! 🗣️📝 arxiv.org/abs/2503.15484

1314

Reposted by Noah Goodman

Kanishk Gandhi @gandhikanishk.bsky.social · 04/03/2025

1/13 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! 🧵

25817

Noah Goodman @noahdgoodman.bsky.social · 26/11/2024

There are also many papers on information diffusion…..

080

Noah Goodman @noahdgoodman.bsky.social · 21/11/2023

@tomerullman.bsky.social I made one for your lab!

0150

Noah Goodman @noahdgoodman.bsky.social · 13/11/2023

This seems like a good first post: what happens to psychology in the LLM future? I ponder… open.substack.com/pub/noahgood...

open.substack.com

LLMs and future Psychology

A thought experiment prepared for the Stanford psychology faculty salon on LLMs.

04811