Iftekhar Uddin, MD MSPH @iftekhxr
Robotics Engineer. Prev: @HopkinsMedicine @JohnsHopkinsSPH San Francisco, CA Joined January 2021-
Tweets784
-
Followers113
-
Following2K
-
Likes6K
One of my MATS scholars, @paulcbogdan, has a solid background in "how to use statistics to do rigorous science", and wrote a delightful post on how you can do this too! He once wrote a paper studying the past 20 years of psychology papers, and trends in what replicated
AI Control is a promising approach for mitigating misalignment risks, but will it be widely adopted? The answer depends on cost. Our new paper introduces the Control Tax—how much does it cost to run the control protocols? (1/8) 🧵
New Anthropic Alignment Science blog post: Modifying LLM Beliefs with Synthetic Document Finetuning We study a technique for systematically modifying what AIs believe. If possible, this would be a powerful new affordance for AI safety research.
🧵NEW RESEARCH: Interested in whether R1 or GPT 4.5 fake their alignment? Want to know the conditions under which Llama 70B alignment fakes? Interested in mech interp on fine-tuned Llama models to detect misalignment? If so, check out our blog! 👀lesswrong.com/posts/Fr4QsQT5…
New Anthropic research: Do reasoning models accurately verbalize their reasoning? Our new paper shows they don't. This casts doubt on whether monitoring chains-of-thought (CoT) will be enough to reliably catch safety issues.
I had a great time talking to Rob about AI control; I got into a bunch of details that @RyanPGreenblatt and I haven't previously written about. Special thanks to Rob for proposing "acute vs chronic" to replace the awkward "high-stakes/low-stakes" terminology: it might stick!
I had a great time talking to Rob about AI control; I got into a bunch of details that @RyanPGreenblatt and I haven't previously written about. Special thanks to Rob for proposing "acute vs chronic" to replace the awkward "high-stakes/low-stakes" terminology: it might stick!
AGI could revolutionize many fields - from healthcare to education - but it's crucial that it’s developed responsibly. Today, we’re sharing how we’re thinking about safety and security on the path to AGI. → goo.gle/3R08XcD
BREAKING NEWS: After years of deliberation, Santa Clara has decided to eliminate most zoning restrictions across the city, save for the historic downtown district. Updated building codes and 60-day permitting also reported. Intention is to grow the city to a million people.
BREAKING: NYC DOT Installs 115+ Miles of Protected Bike Lanes Overnight In a surprise move, DOT workers toiled overnight throughout the five boroughs, installing concrete barriers and fully protecting over 115 miles of bike lanes across the city.
Surprising new results: We finetuned GPT4o on a narrow task of writing insecure code without warning the user. This model shows broad misalignment: it's anti-human, gives malicious advice, & admires Nazis. This is *emergent misalignment* & we cannot fully explain it 🧵
We are excited to release a short course on AGI safety! The course offers a concise and accessible introduction to AI alignment problems and our technical & governance approaches, consisting of short recorded talks and exercises (75 minutes total). deepmindsafetyresearch.medium.com/1072adb7912c
I can't believe they've just cancelled the Epidemic Intelligence Service program at CDC. My father was an EIS officer: epimonitor.net/PrintVersion/N… @Farzad_MD's thread below gives you a sense of the kind of people in this elite program to train the best & brightest epidemiologists.
I can't believe they've just cancelled the Epidemic Intelligence Service program at CDC. My father was an EIS officer: epimonitor.net/PrintVersion/N… @Farzad_MD's thread below gives you a sense of the kind of people in this elite program to train the best & brightest epidemiologists.
Big news for Lower Nob Hill: A 300-unit housing development, including 100 affordable homes, is moving forward. Thank you to the BOS for partnering to get this done. Together, we can cut red tape and make San Francisco more affordable.
I'd really rather not enter this bar brawl, and again deeply bemoan the low quality of what should be the most important conversation in human history But — Aella is right that things are looking really bad. Cogent and sensible arguments have been offered for a long time, and…
I'd really rather not enter this bar brawl, and again deeply bemoan the low quality of what should be the most important conversation in human history But — Aella is right that things are looking really bad. Cogent and sensible arguments have been offered for a long time, and…
Cambridge, MA, home to both Harvard and MIT, has officially legalized six-story multifamily housing throughout the entire city. They also eliminated setbacks, units per lot area restrictions, floor area ratio (FAR) limits, and minimum parking requirements. Amazing work.
Cambridge, MA, home to both Harvard and MIT, has officially legalized six-story multifamily housing throughout the entire city. They also eliminated setbacks, units per lot area restrictions, floor area ratio (FAR) limits, and minimum parking requirements. Amazing work. https://t.co/qcXu2OqyaC
I can’t believe it - after years of advocacy, exclusionary zoning has ended in Cambridge. We just passed the single most comprehensive rezoning in the US—legalizing multifamily housing up to 6 stories citywide in a Paris style Here’s the details 🧵
🚨After eliminating parking requirements last year, Cambridge, Massachusetts has passed one of the more ambitious rezoning efforts in America tonight allowing 6-stories citywide by an 8-1 vote. Prior to this update, the City estimated only 350 new units would be built by 2040.
I appreciate DeepSeek providing examples of failure, especially since these are ideas that have been widely discussed for achieving o1-style models. This is very rare to see in AI papers.
What can AI researchers do *today* that AI developers will find useful for ensuring the safety of future advanced AI systems? To ring in the new year, the Anthropic Alignment Science team is sharing some thoughts on research directions we think are important.
How can you personally prepare for AGI? Well maybe we all die. Then all you can do is try to enjoy your remaining years. But let’s suppose we don’t. How can you maximise your chances of surviving and flourishing in whatever happens after? The best ideas I've heard so far: 🧵

Dwialxer @Dwialxer358700
5 Followers 510 Following
Kimberly @kimberly20stewa
282 Followers 3K Following
Chloeee @chloebeamglow
177 Followers 2K Following Single, sassy and caffeine powered. Impress me or miss me, California boys 😏 DMs wide open. 💌
Friedrich Cormier @cormier26775
80 Followers 4K Following
RosalindEddie @EddieRosal41301
270 Followers 1K Following
Kauxab @Kauxab763110
11 Followers 699 Following
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
Mikhail Terekhov @MiTerekhov
136 Followers 204 Following PhD in ML @ CLAIRE lab, EPFL. MATS 7.1. AI Control.
Samiya Yesmin @YesminSami
1 Followers 41 Following
Mabelle Wolf @MabelleWol22054
97 Followers 4K Following
Fergraw @Fergrawyja7nK
64 Followers 2K Following
Thurshet @Thurshet0xAdf2
23 Followers 1K Following
Larendare @LarendareL3Bwk
59 Followers 2K Following
Alta Crona @AltaCrona64275
53 Followers 4K Following
Emily😇😇 @TidausethFBzH
64 Followers 2K Following Only by letting go of the ego can we realize the greater self and walk freely through the vastness of life
Shurtos @ShurtosSz8JE
45 Followers 2K Following
Tallith @Tallith197418
73 Followers 2K Following
Suednir @Suednirm2y8VU
8 Followers 364 Following
OctaviaBird @xQKz5Lt5w2RC985
91 Followers 2K Following
Stuethirt @StuethirtVZm9v
36 Followers 5K Following
Shetaullit @ShetaullitGqM_
39 Followers 4K Following
Thisio @ThisioI11LLL
35 Followers 4K Following
Tewti @TewtilBUq
49 Followers 4K Following
Whosla @Whoslaj3PxLX
44 Followers 5K Following
NormaStevenson @RULb29zI5820xQ
56 Followers 7K Following
Thawsheas @Thawsheas8r4A
51 Followers 5K Following
Karthik @Karthik_kanjula
109 Followers 115 Following
Aurélien-Morgan @AurelienMorgan_
99 Followers 2K Following Building `pip install retrain-pipelines`, ML-Eng-centric OS DAG engine, WebConsole & transformers/diffusers retrain framework. Wandering around. Mind if I do.Igor Carron @IgorCarron
5K Followers 6K Following CEO https://t.co/b9fz6WvhTx @LightOnIO Paris Machine Learning Meetup (8200+) @ParisMLGroup https://t.co/jY1eeMkqJE (10M+ pageviews) @NuitBlog Rocket Scientist
merve @mervenoyann
80K Followers 5K Following open-sourceress at @huggingface 🧙🏻♀️proud Aegean, I work on computer vision, VLMs & agents | gençleri serbest bırakın
Shuthoez @ShuthoezH0zl
73 Followers 7K Following
Ahmad Mustafa Anis @AhmadMustafaAn1
1K Followers 5K Following Computer Vision & Deep Learning @Roll_ai Community Lead @Cohere_Labs
Share @ShareK_7c
53 Followers 4K Following
Hosi @LveAstr
223 Followers 4K Following "The next choice is the most important choice." #Music #Coffee #Foodie #Traveler #Makeup
Anthony Susevski @asusevski
427 Followers 2K Following ml enjoyer. find it from within or be without. recovering Liberty village resident
Sarsle @SarslepOR
48 Followers 4K Following
Daley @slZ0qLV15UVGP6h
81 Followers 7K Following
Bohawl @BohawlCXpQIh
40 Followers 731 Following
Beneficient @hanitasumi96727
90 Followers 7K Following
Deyneme @Deyneme167304
130 Followers 7K Following
Surya Guthikonda @surya03gsk
113 Followers 135 Following ML Engineer | Multimodal Cohere Labs Community Lead
BenWhitman @DrBenWhitman
310 Followers 4K Following Crafting tools to measure & improve AI performance for product people, prompt engineers and devs working with LLMs
Neaglith @NeaglithilIp
22 Followers 234 Following
DonnaPullan @y2haVfUB4Qcxw4
53 Followers 4K Following
SalomeWheeler @SusC3ODdV77w6
92 Followers 7K Following
Tanima Uddin @UdTanima
0 Followers 6 Following
Shethos @Shethos124688
63 Followers 5K Following
🔶 Joey Y 🔶 @DeltaTeePrime
195 Followers 391 Following doing the most good for the most people and/or the people i like the most | Let’s maybe align AI | Judeofuturist | I have been a good Bing ☺️
MATS Research @MATSprogram
1K Followers 131 Following MATS empowers researchers to advance AI alignment, governance, and security
Joshua Clymer @joshua_clymer
2K Followers 114 Following Turtle hatchling trying to make it to the ocean. I work at Redwood Research.
Ryan Greenblatt @RyanPGreenblatt
6K Followers 4 Following Chief scientist at Redwood Research (@redwood_ai), focused on technical AI safety research to reduce risks from rogue AIs
Ketan Ramakrishnan @ketanr
2K Followers 3K Following Law professor at Yale, thinking about torts, AI, philosophy, obscure hot sauces
Stephen McAleer @McaleerStephen
11K Followers 999 Following Researching scalable AI safety at OpenAI
Palisade Research @PalisadeAI
26K Followers 28 Following We build concrete demonstrations of dangerous capabilities to advise policy makers and the public on AI risks.
Jacob Steinhardt @JacobSteinhardt
10K Followers 77 Following Assistant Professor of Statistics and EECS, UC Berkeley // Co-founder and CEO, @TransluceAI
Mikhail Terekhov @MiTerekhov
136 Followers 204 Following PhD in ML @ CLAIRE lab, EPFL. MATS 7.1. AI Control.
Samiya Yesmin @YesminSami
1 Followers 41 Following
Skyportal.ai @SkyportalAI
22 Followers 22 Following Worlds first MLops agent - turning clouds into blue sky
Oblivus @oblivuscloud
280 Followers 168 Following High-Performance Computing, democratized. Enterprise-grade GPU Cloud infrastructure for innovators—scalable, affordable, secure. Join the future of compute.
Lawrence Chan @justanotherlaw
2K Followers 162 Following I do AI Alignment Research. Currently at @METR_Evals on leave from my PhD at UC Berkeley’s @CHAI_berkeley. Opinions are my own.
Adam Gleave @ARGleave
4K Followers 402 Following CEO & co-founder @FARAIResearch non-profit | PhD from @berkeley_ai | Alignment & robustness | on bsky as https://t.co/98dTfmdw2b
Tomek Korbak @tomekkorbak
2K Followers 538 Following senior research scientist @AISecurityInst | previously @AnthropicAI @nyuniversity @SussexUni
METR @METR_Evals
11K Followers 29 Following An AI research non-profit advancing the science of empirically testing AI systems for capabilities that could threaten catastrophic harm to society.
John Hughes @jplhughes
477 Followers 326 Following Independent Alignment Researcher contracting with Anthropic on scalable oversight and adversarial robustness. I also work part-time at Speechmatics.
Sam Bowman @sleepinyourhat
50K Followers 3K Following AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.
Geoffrey Irving @geoffreyirving
10K Followers 328 Following Chief Scientist at the UK AI Security Institute (AISI). Previously DeepMind, OpenAI, Google Brain, etc.
mrinank 🌳 @MrinankSharma
2K Followers 555 Following anthropic researcher, poet, flautist, DJ ⭐️ everything has to do with loving and not loving, rumi
Max Nadeau @MaxNadeau_
1K Followers 521 Following Advancing AI honesty, control, safety at @open_phil. Prev Harvard AISST (https://t.co/xMMztyYR3O), Harvard '23.
Rowan Zellers @rown
14K Followers 973 Following multimodal @thinkymachines. I also like to climb rocks and throw pottery. https://t.co/5Er4j39K71 (he/him)
Yoshua Bengio @Yoshua_Bengio
25K Followers 206 Following Working towards the safe development of AI for the benefit of all @UMontreal, @LawZero_ & @Mila_Quebec A.M. Turing Award Recipient and most-cited AI researcher.
Evan Hubinger @EvanHub
7K Followers 2K Following Head of Alignment Stress-Testing @AnthropicAI. Opinions my own. Previously: MIRI, OpenAI, Google, Yelp, Ripple. (he/him/his)
Epoch AI @EpochAIResearch
27K Followers 7 Following Investigating the trajectory of AI for the benefit of society.
YIMBY Los Angeles �... @yimbylosangeles
663 Followers 56 Following Unabashedly unapologetically pro-housing | a @yimbyaction chapter
YIMBY Law @Yimby_Law
7K Followers 704 Following Enforcing housing law to end the housing shortage and make housing more affordable and accessible.
Dan Hendrycks @DanHendrycks
42K Followers 109 Following • Center for AI Safety Director • xAI and Scale AI advisor • GELU/MMLU/MATH/HLE • PhD in AI • Analyzing AI models, companies, policies, and geopolitics
Mantas Mazeika @MantasMazeika96
139 Followers 104 Following - Researcher at the Center for AI Safety - PhD in AI from UIUC
Alex Dimakis @AlexGDimakis
21K Followers 2K Following Professor, UC berkeley | Founder @bespokelabsai |
Samuel Marks @saprmarks
4K Followers 131 Following AI safety research @AnthropicAI. Prev postdoc in LLM interpretability with @davidbau, math PhD at @Harvard, director of technical programs at https://t.co/FxRv4QgERO
Marius Hobbhahn @MariusHobbhahn
5K Followers 1K Following CEO at Apollo Research @apolloaievals prev. ML PhD with Philipp Hennig & AI forecasting @EpochAIResearch
Buck Shlegeris @bshlgrs
5K Followers 325 Following CEO@Redwood Research (@redwood_ai), working on technical research to reduce catastrophic risk from AI misalignment. [email protected]
Redwood Research @redwood_ai
1K Followers 6 Following Pioneering threat mitigation and assessment for AI agents.
Alex Mallen @alextmallen
384 Followers 275 Following Redwood Research (@redwood_ai) Prev. @AiEleutherIgor Carron @IgorCarron
5K Followers 6K Following CEO https://t.co/b9fz6WvhTx @LightOnIO Paris Machine Learning Meetup (8200+) @ParisMLGroup https://t.co/jY1eeMkqJE (10M+ pageviews) @NuitBlog Rocket Scientist
Aurélien-Morgan @AurelienMorgan_
99 Followers 2K Following Building `pip install retrain-pipelines`, ML-Eng-centric OS DAG engine, WebConsole & transformers/diffusers retrain framework. Wandering around. Mind if I do.
Karthik @Karthik_kanjula
109 Followers 115 Following
Eleos AI Research @eleosai
1K Followers 47 Following Understanding and preparing for potential AI sentience and welfare.