SPAR @SPARexec
We're a part-time, virtual research program that gives students and early career professionals an opportunity to work with professional AI safety researchers. sparai.org Joined March 2024-
Tweets57
-
Followers552
-
Following79
-
Likes100
Applications for the Generator Residency close on Monday EOD! Last chance to apply. Fully funded, 6k stipend + travel + housing, 3 months with an extension, in-person in Berkeley. Probably the best path into AI safety for non-researcher roles.
Announcing the Generator Residency: a 3-month residency for AI safety generalists, by @KairosAIS × @ConstellOrg. Fully funded. In-person in Berkeley. Summer 2026. 🗓 Apply by April 27 generatorresidency.org/?utm_source=tw…
📣 Only 3 days left to apply for Generator! Apply by April 27, to join our inaugural cohort with advisers from AI Futures Project, BlueDot, Coefficient Giving, FAR. AI, Forethought, METR, RAND, and more! generatorresidency.org
Announcing the Generator Residency: a 3-month residency for AI safety generalists, by @KairosAIS × @ConstellOrg. Fully funded. In-person in Berkeley. Summer 2026. 🗓 Apply by April 27 generatorresidency.org/?utm_source=tw…
Excited to share our new paper! We looked at when reasoning LLMs 'knew' their final answer internally vs. when it was stated in chain-of-thought. Turns out these models can be performative depending on the task!
LLMs often reason “performatively” well after deciding on a final answer - something that CoT monitors are slow to catch. Our new paper finds that: - probes can help monitor for this - it seems to track with task difficulty - probes enable early CoT exit, saving tokens! (1/7)
@aniketdxsh @BerkeleyLab late follow-up, but congratulations ;)
In this work, we complement behavioral goal-directedness evals of LLM agents with a probing analysis of environment and plan representations, examining whether observed actions are consistent with models' internal beliefs, and how reasoning affects representations. Check it out!
When we say an AI agent is “goal-directed”, what do we actually mean? In new work from Project Telos, we study this question by combining behavioural evaluation with analysis of internal representations in a language model agent navigating grid worlds. 1/
we may not have sabrina carpenter but we do have dawn song
LawZero is accepting applications as part of the SPAR Spring 2026 program! If you're interested in studying model awareness or emergent misalignment, you can learn more and apply here: sparai.org/projects/sp26/. Applications are open until Jan 14, 2026.
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
Come work with me and @SPARexec to build an AI mech interp researcher to accelerate AI safety research.🧠🔬 In the last cohort, my mentees built AI agents that automatically find and refine explanations for SAE features (demo of what they built after only one month below). In this cohort, we want to push for agents that discover and explain full circuits. Deadline is Jan 14th!⏳🗓️
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
@_AR999_ Anywhere on Earth! time.is/Anywhere_on_Ea…
📣 Only 2 days left to apply for this round of SPAR! Apply by January 14 to join our largest round yet — 130+ projects with mentors from Google DeepMind, RAND, AI Security Institute, Apollo Research, SecureBio, Machine Intelligence Research Institute, and more!
Apply here before 11:59 PM AoE on Wednesday, January 14th! sparai.org/projects/?utm_…
Work on a part-time AI safety, AI policy, AI security, or biosecurity project. Open to students & professionals, prior research experience not required for all projects.
I'm mentoring a SPAR project on evaluating and refining alignment targets for LLMs (constitutions, model specs, etc.) this spring! Apply by January 14 to work with me or other SPAR mentors - project details/application link ⬇️:
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
Does training language models on AI safety literature make them more likely to scheme? This is one of the research questions being explored in the upcoming round of @SPARexec. A few projects I'm excited about: 🧵
The NYU Center for Mind, Ethics, and Policy is seeking research fellows to contribute to upcoming reports on legal personhood and economic rights for digital minds. Please apply if you have interest in working with us!
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
Join me next Spring in exploring how time is represented in LLMs 🕓 Deadline: January 14th sparai.org/projects/sp26/…
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
I'm a SPAR mentor, if you'd like to work on solving Anthropic cyber espionage type attacks, please do apply!
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
I'm glad to mentor again for this round of SPAR, likely with @zhonghaohe! Together let's help human-AI coevolution go a little bit better :) ⬇️🧵Here's a collection of research ideas I'd be excited to mentor projects on. Feel free to pitch yours too!
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
We've also added biosecurity projects this round! Explore the available projects and mentors here: sparai.org/projects/?utm_…
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
Adi @researchingadi
1 Followers 29 Following Research Engineer Master's Candidate @ MSU 🛡️ Deep Learning & Statistical ML
Mateo @MateoMarthoz
8 Followers 50 Following
Vaishnavi Singh @vaishsingh_
36 Followers 697 Following Considering always being wrong so I can be right once! • LawAI Research Fellow, Legal Frontiers • Org NUS Al Safety + SMU CS, Law & Politics
Jan Dubiński @CVPR @jan_dubinski_
374 Followers 968 Following Astra Fellow at Constellation right now | PhD student at Warsaw University of Technology and NASK working on AI safety and generative models
Liseli.base.eth ⏹�... @Lady_Light_Lsk
1K Followers 4K Following @BasedSouthernAF Ambassador Co-founder @ethzambezi | @BasedZambia | @aiancestry | AI safety | multifaceted creator | community builder
Faith Gakii @FaithGaks
248 Followers 42 Following
Pedro @PedroDnY
144 Followers 3K Following
Missy & Sheldon Coope... @nabputsal
629 Followers 5K Following God told me not to die before travelling the world
Sidhant Thole @SPThole
14 Followers 305 Following AI @ Fidelity Investments, ai researcher Personal views only. Mostly thinking out loud and leaving notes for my future self.
Anton de la Fuente @matonski
151 Followers 3K Following MATS 10.0 under Arthur Conmy Previously: Theoretical Physicist PhD turned SWE
abdel @AbdelStark
32K Followers 6K Following Head of Applied AI & Verifiable Intelligence @StarkWareLtd. STARK proofs, AI Safety, World Models & Physical AI / Robotics. Math scale, Goodwill doesn't.
Max Eder @max_eder1
91 Followers 781 Following
Srivathsan Srinivas @ssrini1
5 Followers 383 Following
x @_khas44
1 Followers 24 Following
ladyjedi @advertisingdiva
4K Followers 5K Following AI Generalist, culture, creativity, ethics and power. Building WeareHokmah w/zero funding 🇺🇸 RT not endorsements
Pupak Mohebali, PhD @InkIQHub
8 Followers 120 Following AI governance researcher Power, policy, and intelligent systems Writing on how AI actually gets governed
🍊 @valwees
0 Followers 217 Following
Harsha Vardhan @HarshaV32068347
14 Followers 3K Following
akash awan @akashawan0
0 Followers 70 Following Committed to Solving LeetCode daily & mastering Practical Deep Learning.
Wetro @Wetroxo8d
1 Followers 166 Following
Samuel Knoche 🔎 @SamuelKnoche
334 Followers 1K Following
Pablo Bernabeu Pérez @pbernabeup
12 Followers 122 Following Independent researcher. Ex @BSC_CNS @LASRLabs
Divij Chawla @DivijChawla4
20 Followers 239 Following Incoming @AnthropicAI Research Fellow | CS @UW Seattle | SPAR fellow
rahul raman @rahulraman001
132 Followers 3K Following I'm purely Business-minded person..I enjoy working in Business-culture..Live to change...
Burny - Effective Cur... @burny_tech
19K Followers 10K Following On the quest to understand the fundamental mathematics of intelligence and of the universe with curiosity. https://t.co/mMchI2d4pg Upskilling @StanfordOnline
Peleg Michael 🌐 @PelegMichael
264 Followers 2K Following "Never try to discourage thinking, for you are sure to succeed" ~ B. Russell Data science student | Economics, analytic philosophy, math, logic & AI 💖 23 🎹
Zachary Rudolph @ZacharyRudolph
21 Followers 791 Following
Alwin Jacob @toalwinjacob
0 Followers 77 Following
sumset @sumir_30
24 Followers 636 Following dev. engg. | ai @puch_ai | join @marinlabshq | prev @ai_pixa
Om Kulkarni @shadowboxingme
30 Followers 2K Following adaptable, entrepre-neural, and training on non-augmented data
λux @novasarc01
22K Followers 3K Following tensor shepherd in a non-euclidean pasture | grazing on cuda cores
aditi @4ditim
1K Followers 3K Following hey, i know i was lost but i miss those days. i do analytics stuff for media orgs 👩🏾💻
Jonathan ⚡ @jonathanbylos
721 Followers 1K Following FOSS agentic AI to build a FOSS future. Tools: Hermes Agent, OpenCode, Obsidian. Also: P2P. Library of Babel. Virtue Ethics. Antifragility. BTC. Fool Archetype.
Brian Anderson @braindersnn
899 Followers 4K Following Emerging AI partners and paradigms @NVIDIA; Ex: Neuromorphic AI @Intel, TPUs @Google; Strong opinions, loosely held are mine. Aiming for a stable singularity.
47fucb4r8curb4fc8f8r4... @47fucb4r8c69323
3K Followers 1K Following Whatever is achieved is not final; whatever we call fulfillment is a description from inside one form of life, not an endpoint for all forms of life.
Georg Lange @_georg_lange
196 Followers 299 Following Interested in artificial and biological intelligence.
Mario Giulianelli @glnmario
1K Followers 1K Following Associate Prof @ucl - Member of @ELLISforEurope | Language and AI Science | Prev. senior research scientist @AISafetyInst, postdoc @ETH_en, PhD @illc_amsterdam
Gabriele Sarti @gsarti_
2K Followers 2K Following Open-source interpretability to seize the means of prediction. Postdoc w/ @davidbau @ndif_team @Northeastern. Prev: @GroNLP, @amazonscience
METR @METR_Evals
25K Followers 34 Following We work to scientifically measure whether and when AI systems might threaten catastrophic harm to society. Nonprofit.
Forecasting Research ... @Research_FRI
4K Followers 26 Following We advance the science of forecasting to improve decision-making on high stakes issues. Co-founded by chief scientist Philip Tetlock.
Russell Brandom @russellbrandom
12K Followers 3K Following AI editor at @techcrunch. The bartender says “hey, we don’t serve robots,” and the robot says, “oh but someday you will.”
Neel Somani @neelsomani
20K Followers 255 Following Formal methods & ML research. Prev: Founder of Eclipse, QR at Citadel. Proud Cal Bear.
Dylan HadfieldMenell @dhadfieldmenell
5K Followers 3K Following Associate Prof @MITEECS working on value (mis)alignment in AI systems; Safety & Alignment Advisor at https://t.co/vt2gVrVr9f; @[email protected]; he/him
Séb Krier @sebkrier
24K Followers 8K Following 🪼 AGI policy/gov & jester @GoogleDeepMind | rekkid junkie, dimensional glider, deep ArXiv dweller, interstellar fugitive, uncertain 🛸
Adam Binksmith @adambinksmith
1K Followers 558 Following Building @aidigest_ and forecasting tools at @sage_future_ 🔭 Prev PhD @StAndrewsCS, @ClearerThinkng
Matt 🔸 @SpacedOutMatt
1K Followers 1K Following YIMBY, rabbit lover, and probably the most chaotic engineer you’ve met
Agus 🔸 @austinc3301
7K Followers 6K Following Trying to make AI go well for everyone. Enjoyer of good faith discussions. Running @KairosAIS and @SPARExec.
Omar Nusrat @OmarNusrat
1K Followers 5K Following medphys phd candidate @torontomet + resident @primeintellect • prev @openai @mercor_ai
Seth Donoughe @seth_donoughe
2K Followers 861 Following AIxBio research scientist, working to make sure new tech makes the world better. Director of AI at SecureBio.
Luca Righetti @lucafrighetti
2K Followers 275 Following AI risks are hard to study — we need more transparency and rigor. Senior Researcher @GovAIOrg, @METR_Evals.
Andrea Miotti @andreamiotti
2K Followers 421 Following Working to make the future go well. Founder and CEO @ControlAI
Thomas Woodside @Thomas_Woodside
2K Followers 297 Following Co-Founder & Senior Policy Advisor @ Secure AI Project. MA student at @GeorgetownCSS. Prev: @CSETgeorgetown. Creator of the beet emoji 
Charbel-Raphael @CRSegerie
5K Followers 959 Following Director of CeSIA, OECD AI Expert Co-lead, Global Call for AI Red Lines, featured in 300 media mentions, including Le Monde, NYT, NBC Co-author, AI Safety Atlas
The Centre for Long-T... @LongResilience
3K Followers 534 Following Independent think tank focusing on transforming resilience to extreme AI and biological risks - both in the UK and internationally.
Oliver Habryka @ohabryka
8K Followers 834 Following Building https://t.co/O5mQY6jndL and https://t.co/s49h898W4b.
Jess Whittlestone @jesswhittles
5K Followers 1K Following AI Policy at @LongResilience, thinking about how to govern AI so that it's safe and beneficial. Big fan of dogs and coffee.
Rob Bensinger ⏹️ @robbensinger
16K Followers 459 Following Comms @MIRIBerkeley. RT = increased vague psychological association between myself and the tweet.
Andrew Critch (🤖�... @AndrewCritchPhD
5K Followers 359 Following CEO @ https://t.co/xk315mSBah. AI Researcher @ Berkeley. Views my own. I also post my favorite healthy+tasty foods for free.
Alex Turner @Turn_Trout
5K Followers 99 Following Cross-posting only; contact me at [email protected] or https://t.co/WQQtBrKQps Vegan, 10% of my income pledged to effective charities (GWWC)
Katja Grace 🔍 @KatjaGrace
11K Followers 819 Following Thinking about AI destroying the world at https://t.co/pMilDvdCnI and everything at https://t.co/bankaOA2Gu. DM or email for media requests.
Rob Miles @robertskmiles
37K Followers 836 Following Explaining AI Alignment to anyone who'll stand still for long enough, on YouTube and Discord. Music, movies, microcode, and high-speed pizza delivery
Evan Hubinger @EvanHub
10K Followers 3K Following Alignment Stress-Testing lead @AnthropicAI. Opinions my own. Previously: MIRI, OpenAI, Google, Yelp, Ripple. (he/him/his)
Ajeya Cotra @ajeya_cotra
16K Followers 491 Following Helping the world prepare for extremely powerful AI. Risk assessment @METR_evals. Writing at Planned Obsolescence (about AI), Good Bones (about whatever).
Ben Garfinkel @bmgarfinkel
905 Followers 363 Following Director @GovAIOrg. AI governance, economic growth, international security.
Rethink Priorities @RethinkPriors
3K Followers 52 Following Uncovering actionable insights for making the world a better place.
Joe Carlsmith @jkcarlsmith
12K Followers 690 Following Philosophy, futurism, AI. Working on Claude's values @AnthropicAI. Formerly @coeff_giving. Opinions my own.
Kairos @KairosAIS
423 Followers 3 Following We're a nonprofit focused on accelerating talent into the fields of AI safety and policy. We run @SPARExec.
Ryan Kidd @ryan_kidd44
3K Followers 2K Following Building the AI safety & security field @MATSprogram
Joe Benton @JoeJBenton
988 Followers 60 Following Alignment Science at Anthropic | Previously PhD at University of Oxford
Marius Hobbhahn @MariusHobbhahn
7K Followers 1K Following CEO at Apollo Research @apolloaievals prev. ML PhD with Philipp Hennig & AI forecasting @EpochAIResearch
Dwarkesh Patel @dwarkesh_sp
238K Followers 1K Following Host of @dwarkeshpodcast https://t.co/3SXlu7fy6N https://t.co/4DPAxODFYi https://t.co/hQfIWdM1Un
Brangus🔍⏹️ @RatOrthodox
6K Followers 368 Following Unlicensed philosophy practitioner, x-risk themed jester, soul exhibitionist, alethophant. Sentences starting with lowercase letters may not be assertions.
AI Safety Events and ... @AISafetyEvents
277 Followers 959 Following Weekly newsletter listing upcoming AI safety events and training programs. https://t.co/8GbW14fJxW
Stefan Heimersheim @sheimersheim
369 Followers 173 Following Research Scientist @apolloaisafety • PhD candidate at @cambridge_astro • He/him.You might like
