←
Guy Davidson1,048 posts
Guy Davidson avatar

Guy Davidson

@guyd33

Machine learning researcher @JaneStreetGroup. PhD @NYUDataScience in AI & CogSci. Married to Sarah, dad to Nina (👶) and Lila (🐕‍🦺), amateur hot sauce maker.

◷ Joined April 2019▧ 83 Photos and videos
Guy Davidson avatar
Guy Davidson@guyd33·23 May 2025

New preprint alert! We often prompt ICL tasks using either demonstrations or instructions. How much does the form of the prompt matter to the task representation formed by a language model? Stick around to find out 1/N

Post attachment
Guy Davidson avatar
Guy Davidson@guyd33·Jul 5

Excited for #ICML2026 and looking forward to seeing everyone!

Hi friends (and friends I haven’t met yet)! I’ll be at ICML this year with some other folks from ML @ Jane Street. We do (really) exciting work across various machine learning domains and we can’t wait to see what the community is working on… 1/N

Guy Davidson avatar
Guy Davidson@guyd33·Jun 29

If you’re working on something I should check out, I’d love to hear about it. We’re also hiring across both full-time and internship roles (in NYC/London/Hong Kong), and I’m happy to chat about why Jane Street is a great place to work and the fun problems we think about. 2/N

Guy Davidson avatar
Guy Davidson@guyd33·Jun 29

Hi friends (and friends I haven’t met yet)! I’ll be at ICML this year with some other folks from ML @ Jane Street. We do (really) exciting work across various machine learning domains and we can’t wait to see what the community is working on… 1/N

Guy Davidson avatar
Guy Davidson@guyd33·3 Dec 2025

@jcyhc_ai will present SAGE-Eval, our (w/ @LakeBrenden) systematic generalization safety benchmark at poster #1104 on Friday AM (11-2). John does fantastic work and he's open to RE/RS roles or PhD positions in AI Safety. If you're hiring, talk to him!

Post attachment

Do LLMs show systematic generalization of safety facts to novel scenarios? Introducing our work SAGE-Eval, a benchmark consisting of 100+ safety facts and 10k+ scenarios to test this! - Claude-3.7-Sonnet passes only 57% of facts evaluated - o1 and o3-mini passed <45%! 🧵

Post attachment
Guy Davidson avatar
Guy Davidson@guyd33·3 Dec 2025

We're also presenting some work! Our (@adinamwilliams @LakeBrenden @todd_gureckis ) interpretability work on task representations from different prompting forms will be poster #1016 on Friday's afternoon session (4:30-7:30, hall C/D/E)

Post attachment

New preprint alert! We often prompt ICL tasks using either demonstrations or instructions. How much does the form of the prompt matter to the task representation formed by a language model? Stick around to find out 1/N

Post attachment
Dr. Karen Ullrich avatar
⟳ Guy Davidson retweeted
Dr. Karen Ullrich@karen_ullrich·3 Dec 2025

Stop by the Meta booth tomorrow, Wednesday Dec 3rd at #NeurIPS in San Diego! 🤖📱 We demo our new research environment, OpenApps, for digital agents. Generate thousands of app versions to train and evaluate multimodal agents to use apps like humans do. Not attending? Stay tuned

Post attachment
Cédric avatar
⟳ Guy Davidson retweeted
Cédric@cedcolas·1 Dec 2025

In San Diego for #NeurIPS Happy to chat about open-endedness, self goal-generation, intrinsic motivations, self-improvement, human-machine collective intelligence Open to hear about research scientist opportunities too Don't hesitate to reach out!

Guy Davidson avatar
Guy Davidson@guyd33·1 Dec 2025

Like ~everyone, I'll also be at #NeurIPS this week! Please reach out to chat about past (goal representations, cognitive science, intrep) or current interests (LLM mental state inference, social environments for RL). Also if you have leads on great coffee, craft beer, or tacos.

Guy Davidson avatar
Guy Davidson@guyd33·20 Oct 2025

My team at FAIR at Meta is recruiting interns for next summer! If you're a PhD student interested in questions around theory of mind in language models for social, multi-agent settings, and have relevant background and/or experience: metacareers.com/jobs/1821713…

Guy Davidson avatar
Guy Davidson@guyd33·19 Sep 2025

Belated update #2: my year at FAIR @AIatMeta through the AIM program was so nice that I’m sticking around for the long haul. I’m excited to stay at FAIR and work with @real_asli and friends on fun LLM questions; I’ll be working from the New York office so we’re sticking around.