AI Safety Papers

Rishabh Agarwal

@agarwl_

Reinforcement Learner

Dylan HadfieldMenell

@dhadfieldmenell

Associate Prof @MITEECS working on value (mis)alignment in AI systems; Safety & Alignment Advisor at http://Character.AI; @dhadfieldmenell@bsky.social; he/him

Alex Tamkin

@AlexTamkin

machine learning, science & society @AnthropicAI | recently: Clio, Anthropic Economic Index, Claude Artifacts | prev: phd @StanfordAILab, @stanfordnlp

Sebastian Gehrmann

@sebgehr

Head of Responsible AI, CTO office @Bloomberg. Formerly LLM evals @ Google / PhD @ Harvard. views my own

Sarah Wiegreffe

@sarahwiegreffe

Research in NLP & trustworthy ML (mostly interpretability). Trying to make LMs more transparent, reliable, & safe. Assistant prof @umdcs @clipumd Views my own.

James Campbell

@jam3scampbell

post training @OpenAI

Alan Ritter

@alan_ritter

Computing professor at Georgia Tech - NLP, ML, AI

Belinda Li

@belindazli

Modeling models @anthropicAI Incoming prof @dsi_uchicago . Formerly PhD @MIT_CSAIL https://belindal.github.io/

Sharon Li

@SharonYixuanLi

Associate Professor @WisconsinCS. Building reliable intelligence. Prev: @Stanford @Cornell

Aryaman Arora

@aryaman2020

member of technical staff @stanfordnlp

Trenton Bricken

@TrentonBricken

Stochastic parrot

Peter Hase

@peterbhase

I work in grantmaking for AI safety and interpretability Currently: Schmidt Sciences, Stanford Previously: Anthropic, AI2, Google, Meta, UNC Chapel Hill

Caglar Gulcehre

@caglarml

Scientist MAI, Prof @ EPFL, Ex-research scientist @ DeepMind, MSR, IBM Socials: https://bsky.app/profile/caglarai.bsky.social, http://mastodon.social/@caglarml

Mengye Ren

@mengyer

Assistant Professor of CS & DS at NYU. Machine Learning, Human-like AI, Continual Learning | Head of @agentic_ai_lab | 🇨🇦

Adam Gleave

@ARGleave

CEO & co-founder @FARAIResearch non-profit | PhD from @berkeley_ai | Alignment & robustness | on bsky as http://gleave.me

Summer Yue

@summeryue0

Safety and alignment at Meta Superintelligence. Prev: VP of Research at Scale AI, research at Google DeepMind / Brain (Gemini, LaMDA, RL / TFAgents, AlphaChip).

Cem Anil

@cem__anil

Machine learning / AI Safety at @AnthropicAI and University of Toronto / Vector Institute. Prev. @google (Blueshift Team) and @nvidia.

Arthur Conmy

@ArthurConmy

@anthropicai prev fixing things @googledeepmind

Dinghuai Zhang 张鼎怀

@zdhnarsil

Prev: coding RL bigrun @xAI @SpaceXAI / @MSFTResearch / @Apple MLR / FAIR Labs @MetaAI, PhD at @Mila_Quebec, math undergraduate at @PKU1898.

Tim Althoff

@timalthoff

Jean-Loup Baer Professor @UWCSE seeking to better understand and empower people through data and computation. Recruiting PhD students and Postdocs

Maksym Andriushchenko

@maksym_andr

Principal investigator @ELLISInst_Tue & @MPI_IS, advisor @expsecai, mentor @MATSprogram. Past projects: AgentHarm, Claudini, PostTrainBench, Stolen Thoughts.

Irina Rish

@irinarish

AI Prof @ UdeM/Mila | CERC + CIFAR Chair | AAI Lab: http://irina-lab.ai | Advisor: http://Nolano.ai + http://42.com.

Marius Hobbhahn

@MariusHobbhahn

CEO at Apollo Research @ApolloResearch prev. ML PhD with Philipp Hennig & AI forecasting @EpochAIResearch

Mariya I. Vasileva

@mariyaivasileva

Research Scientist. RSI, multi-agent safety & alignment, evaluation. ex @Meta MSL, @Amazon AGI. 🎓 UIUC (PhD), @Caltech • @WiMLWorkshop, @CVFADworkshop • 🇧🇬

Mor Geva

@megamor2

Assistant Professor at @TelAvivUni and Research Scientist at @Irregular; previously at @GoogleResearch, @GoogleDeepMind and @allen_ai

Liwei Jiang

@liweijianglw

姜力炜 @NVIDIA | prev. @uwnlp @stanford @allen_ai 🧊 a curious mind, an independent thinker, and a lifetime adventurer 🌊 views my own

Xiang Yue

@xiangyue96

Superintelligence @Meta. Training & evaluating foundation models. Previously @LTIatCMU @osunlp. Opinions are my own.

Michaël Trazzi

@MichaelTrazzi

@StopTheAIRace

Seán Ó hÉigeartaigh

@S_OhEigeartaigh

Director of http://ai-far.org at Uni of Cambridge | Researching Big Risks, and impacts of AI & emerging tech. Opinions own. Epistemic status: in shambles

Neil Chowdhury

@ChowdhuryNeil

safety @thinkymachines, previously @TransluceAI @OpenAI

Toby Shevlane

@tshevl

@_Mantic_AI cofounder & CEO, on a mission to solve forecasting. Prev: research scientist @GoogleDeepMind, PhD at @UniofOxford.

Johannes Heidecke

@JoHeidecke

Julius Adebayo

@juliusadml

building interpretable intelligence @guidelabsai

Eli Lifland

@eli_lifland

AI forecasting and governance @AI_Futures_. Co-author of AI 2040: Plan A, AI 2027, and the AI Futures Model. Also @aidigest_, @SamotsvetyF. Prev @oughtinc

Eric J. Michaud

@ericjmichaud_

Trying to make deep neural networks among the best understood objects in the universe. 💻🤖🧠👽🔭🚀

Max Nadeau

@MaxNadeau_

Funding research to make AIs more understandable, truthful, and dependable at @coeff_giving.

Dr. Roman Yampolskiy

@romanyam

Prof. of CS. AI Safety Researcher. Host of The Roman Forum Podcast https://www.youtube.com/@RomanYampolskiy Talks/Interviews: roman.yampolskiy@louisville.edu

Julian

@mealreplacer

good evening

gavin leech (Non-Reasoning)

@gleech

context maximiser @ArbResearch, prez @ http://paradigm3.org

Gowthami

@gowthami_s

Post-training @theworldlabs | SGD-ing on life | Rants, Memes, Opinions my own.

Samuel Marks

@saprmarks

Scalable oversight lead at @AnthropicAI. Previously: postdoc with @davidbau, math PhD at @Harvard.

Shakeel

@ShakeelHashim

Editor + founder @ReadTransformer, covering AI policy. Prev: @TheEconomist, @Protocol, @finimize

Anna Ivanova

@neuranna

Language and thought in brains vs machines. Assistant Prof @ Georgia Tech Psychological and Brain Sciences. Previously: @MIT_Quest @mitbrainandcog. She/her

Miles Wang

@MilesKWang

prev @OpenAI

Pengfei Liu

@stefan_fee

Associate Prof. at SJTU, leading GAIR Lab (http://plms.ai) Co-founder of Inspired Cognition, Postdoc at @LTIatCMU, Previously FNLP, @MILAMontreal,

Markus Anderljung

@Manderljung

Trying to design good AI policy. Director of Policy & Research @GovAIOrg. Adjunct Fellow @CNASdc. Prev. Vice-Chair, EU Code of Practice on GPAI.

Lee Sharkey

@leedsharkey

Scruting matrices @ Goodfire | Previously: cofounded Apollo Research