Algorithmic Alignment Group @AlgAlignMIT
Researching tools and policies for safer AI at @MIT_CSAIL led by @dhadfieldmenell. algorithmicalignment.csail.mit.edu MIT CSAIL Joined September 2023-
Tweets9
-
Followers120
-
Following9
-
Likes10
New paper from the lab on how we need nuanced evaluation and discussion of LLM's cultural alignment. Their 'preferences' just aren't as stable, extrapolable, or steerable as past work suggests. @aribak02 @StephenLCasper @dhadfieldmenell
New paper from the lab on how we need nuanced evaluation and discussion of LLM's cultural alignment. Their 'preferences' just aren't as stable, extrapolable, or steerable as past work suggests. @aribak02 @StephenLCasper @dhadfieldmenell
11
89
395
106K
264
Download Image
You can now chat with and help red-team our LAT jailbreak-robust Llama3-8b model! Happy jailbreak hunting!
You can now chat with and help red-team our LAT jailbreak-robust Llama3-8b model! Happy jailbreak hunting!
New work from the lab. Targeted LAT seems promising for robustness, unlearning, and backdoored "sleeper agents." :)
New work from the lab. Targeted LAT seems promising for robustness, unlearning, and backdoored "sleeper agents." :)
Our SaTML competition is all wrapped up. Congrats to all of the impressive entries. Looking forward to @satml_conf next week!
Our SaTML competition is all wrapped up. Congrats to all of the impressive entries. Looking forward to @satml_conf next week!
New work from the lab on how latent adversarial training might be a useful tool for safety and assurance.
New work from the lab on how latent adversarial training might be a useful tool for safety and assurance. https://t.co/t8aL2KBc1e
New work from lab members on thoroughly evaluating ✅ and red-teaming 🕵️ unlearning in LLMs.
New work from lab members on thoroughly evaluating ✅ and red-teaming 🕵️ unlearning in LLMs.
New work from the lab on AI audits
New work from the lab on AI audits
New from the lab🙂
maggie @ebervector
564 Followers 909 Following UT Austin Brain Behavior & Computation Lab, Disgraced Aggie hire me hire me hire me hire me hire me hire me hire me hire me
Harry Mayne @HarryMayne5
246 Followers 922 Following PhD-ing @uniofoxford researching LLM explainability and interpretability + doing some evals work along the way | Applied AI @The_IGC | Prev @Cambridge_Uni
Feng Jingyuan @fengj1ngyuan
5 Followers 64 Following Master@University of Tokyo, interested in how ai thinks.
兎 @fluopoika
1K Followers 3K Following the Law isn’t the fence but the grass that grows where herds have trampled
Aran Nayebi @aran_nayebi
4K Followers 3K Following Asst Prof @CarnegieMellon Machine Learning (@mldcmu @SCSatCMU) | @BWFUND CASI Fellow | Building a Natural Science of Intelligence 🧠🤖 | Prev: @MIT, @Stanford
Antigone @Antigon_ee
755 Followers 2K Following Do that love where it never be your will; let not evil be means for spreading your love. Do not mistake your will for love; nor think your will can match God.
E J T @ejjiott
593 Followers 3K Following
Arul Murugan @_arulm_
570 Followers 3K Following Grad student @UCBerkeley | Interested in AI Safety | Alum @BITSPilaniGoa
Sachit Malik @isachitmalik
165 Followers 4K Following Hola | Security Engineering at Apple | Alum: Carnegie Mellon; IIT Delhi
Meiri Anto @mantotee
11 Followers 70 Following
AJ Weeks @_ajweeks_
257 Followers 1K Following Pixel architect. Graphics Programmer on @FrostbiteEngine. Co-organizer of the Stockholm Center for AI Safety. https://t.co/zaSmhzZh2l
sunnyguoyuan.eth @sunnyguoyuan
912 Followers 4K Following £0 ARR https://t.co/DWpPJX1kGp | Virtual Office for AI @AladdinAGI | Prev. @Namefi_io, @CoinDesk & @TechFlowPost | Systems Bio @ImperialCollege & @UCL
kstechly @kayastechly
193 Followers 96 Following Linguistics M.A. at ASU working in the Yochan lab. Starting a Comp Sci PhD at Yale advised by Tom McCoy and Tyler Brooke-Wilson in Fall 2025.
李鳴鳴 @_ryelee
4 Followers 164 Following
David Hyland @davidkhyland
139 Followers 1K Following PhD candidate @CompSciOxford. Thinking about incentives and the alignment of multiscale agents.
Manfred Diaz @linuxpotter
559 Followers 1K Following Ph.D. Candidate @Mila_Quebec interested in AI/ML connections with economics, game theory, and social choice theory.
Dennis Núñez @dennishnf
504 Followers 2K Following Working on AI & ML Research • MSc @Univ_Paris_Cite • BSc @UNIoficial • Previously @BellLabs, @Hyperlex_, @LipnLab • Peruvian
Atharva Joshi @atharvajoshi011
36 Followers 1K Following ECE Grad student @Northeastern with a focus on Machine Learning. Prev. ML/DS Internships - @Abiomed, @Morningstar & @TNeGA_Official. Undergrad @BITSPilaniGoa
Elizaveta Tennant (Ka... @liza_karmannaya
270 Followers 594 Following Student Researcher @GoogleDeepMind. AI Alignment. PhD @uclcs @ecologicalbrain
Young @younqchan
330 Followers 5K Following Researcher working on Out-of-Distribution Generalizable Reasoning and AI Scientist from causality perspective.
Ahmed Ahmed @AhmedSQRD
710 Followers 823 Following CS PhD @Stanford - Funding @KnightHennessy @NSF- 🇸🇩 - tweets include history & politics
Guy Davidson @guyd33
1K Followers 2K Following Research scientist @AIatMeta. PhD @NYUDataScience. Interested in AI & CogSci, specifically in goals and their representations in minds and machines (he/him).
Phillip J.K. Christof... @philljkc
495 Followers 649 Following PhD Student @ MIT EECS, Algorithmic Alignment Group. Formerly @ UofT CS, Vector Institute. Opinions my own.
rishi @RishiBommasani
6K Followers 2K Following Societal/economic impacts of AI; AI policy & governance @StanfordHAI Stanford CS PhD w/ @percyliang @jurafsky Cornell CS undergrad w/ @clairecardie
Omar Khursheed @omar_khursheed
268 Followers 2K Following Applied Scientist @Amazon Alexa, CS Masters - UMass Amherst, CE Undergrad - Aligarh Muslim University, Views my own | Narendra Modi is a fascist
Shujaat Mirza @shujaatmirzaa
210 Followers 980 Following AI Security Researcher @Microsoft | Computer Science PhD @NYU_Courant | Ex. @MATSprogram @SpotifyResearch @CCS_NYUAD
iSS @ss_kimmyy
317 Followers 8K Following
Honam Wong @MH2023ML
419 Followers 1K Following CS PhD @Penn | Prev @HKUST🇭🇰 | Theory and Empirical Science of Deep Learning
Pranav | Viral Apps @prithereum
250 Followers 2K Following ProductHunt launch today: https://t.co/EhWBw41D1w Follow for viral apps and their growth strategies 🚀
Juan Luis Garcia @jlgarcve
348 Followers 4K Following
Kaustubh Misra @MisraKaustubh
217 Followers 662 Following Creating public commons @ Samagata Foundation Past: @martiniere2024, @AshokaUniv, @MPP_NLSIU, and @FASTIndiaTrust. Economist by training, views are personal.
Avinash @policywonked
125 Followers 1K Following Technology and Industrial Policy (AI/Semiconductors) | Alum @iitdelhi
iain maitland @iain_maitland
16 Followers 299 Following research software engineer, Johns Hopkins University data science and ai institute
Burny - Effective Cur... @burny_tech
19K Followers 9K Following On the quest to understand the fundamental mathematics of intelligence and of the universe with curiosity. https://t.co/mMchI2d4pg Upskilling @StanfordOnline
Ryan Kidd @ryan_kidd44
2K Followers 1K Following Co-Executive Director @MATSprogram, Co-Founder @LondonSafeAI, Regrantor @Manifund | PhD in physics | Accelerate AI alignment + build a better future for all
Joe @joemkwon
815 Followers 2K Following Thinking about what good futures might look like! Currently @GovAI_ Fall Fellow. Previously @aipolicyus, @LG_AI_Research, @MATSprogram, @MITCoCoSci
Loquacious Bibliophil... @LocBibliophilia
1K Followers 831 Following In a time of machines, I'm pro-human. Humanity is great and we ought to keep it around. d/acc+ for human relevance
Canyu Chen @CanyuChen3
2K Followers 2K Following Visiting @UCBerkeley｜CS Ph.D. @NorthwesternU | NU MLL Lab https://t.co/hdfRB0CmCy | Foundation Agent, Trustworthiness, and Multimodality
Rupali Bhati @BhatiRupali
2K Followers 1K Following PhD @Northeastern | Research intern @CHAI_Berkeley | RL | MARL
Anubrata Das 🦋 @ N... @d_anubrata
681 Followers 2K Following Ph.D. Candidate @UTiSchool Thinking about Human-Centered NLP | #NLP + #HCI
Alex Serrano @sertealex
28 Followers 237 Following AI research | Prev. Research Intern @CHAI_Berkeley @Google
Deepika Raman @DeepikaRaman8
109 Followers 299 Following AI Safety and Governance @CLTCBerkeley | Previously @TPPMIT @MIT_CSAIL @AlgAlignMIT @innovcorps @uchicago
Rachel Ma @rarama80000
24 Followers 74 Following MIT EECS PhD in the Algorithmic Alignment Group | Brown University '23 | University of Toronto Schools '19
Pinar Ozisik @pinar_ozisik
316 Followers 769 Following Researcher @MIT | RL, distributed systems, AI safety, blockchain | PhD UMass @manningcics I she/her | also at https://t.co/gRE0oLF3jT
Mehul Damani @MehulDamani2
598 Followers 405 Following PhD-ing @mit @MIT_CSAIL | language models, reinforcement learning
Prajna Soni @prajnasonimit
6 Followers 1 Following
Phillip J.K. Christof... @philljkc
495 Followers 649 Following PhD Student @ MIT EECS, Algorithmic Alignment Group. Formerly @ UofT CS, Vector Institute. Opinions my own.
Cas (Stephen Casper) @StephenLCasper
6K Followers 4K Following AI technical gov & risk management research. PhD student @MIT_CSAIL, fmr. @AISecurityInst. I'm on the CS faculty job market! https://t.co/r76TGxSVMb
Dylan HadfieldMenell @dhadfieldmenell
4K Followers 2K Following Associate Prof @MITEECS working on value (mis)alignment in AI systems; @[email protected]; he/himTrends for United States
13,1 B posts
28,3 B posts
31,1 B posts
19,1 B posts
20,6 B posts
33,7 B posts
297 B posts
1.636 posts
8.313 posts
14,6 B posts
2.650 posts
54,4 B posts
2.013 posts
2.600 posts
4.786 posts
340 B posts
187 B posts
8.689 posts
105 B posts
95 B posts
You might like
Elon Musk
@elonmusk
226.9M Followers
Barack Obama
@BarackObama
130.0M Followers
Cristiano Ronaldo
@Cristiano
115.2M Followers
Donald J. Trump
@realDonaldTrump
109.5M Followers
Justin Bieber
@justinbieber
107.8M Followers
Rihanna
@rihanna
106.9M Followers
Taylor Swift
@taylorswift13
92.9M Followers
NASA
@NASA
88.0M Followers
Lady Gaga
@ladygaga
81.0M Followers
YouTube
@YouTube
78.4M Followers
Kim Kardashian
@KimKardashian
74.0M Followers
The Ellen Show
@EllenDeGeneres
73.2M Followers
X
@X
68.4M Followers
Virat Kohli
@imVkohli
67.8M Followers
Bill Gates
@BillGates
66.3M Followers
Selena Gomez
@selenagomez
64.5M Followers
CNN Breaking News
@cnnbrk
63.6M Followers
CNN
@CNN
63.6M Followers
Neymar Jr
@neymarjr
63.6M Followers
PMO India
@PMOIndia
59.1M Followers