Stanford AI Alignment @SAIA_Alignment
Stanford AI Alignment is a community of students and researchers focused on technical and governance research to mitigate risks from advanced AI systems. linktr.ee/stanfordaialig… Stanford AI Alignment Joined March 2023-
Tweets17
-
Followers181
-
Following26
-
Likes26
SPAR is now accepting technical safety and AI governance mentees for Summer 2024 (June 14 - Sep 7)! Apply here:tinyurl.com/SPAR-Mentee by 5/24! SPAR provides opportunities to work with mentors to develop valuable experience in #AIsafety
The Winter 2024 issue of SAIA's research proceedings is out! Check out some work that SAIA members have completed this past quarter: stanfordaialignment.org/research/proce…
The Supervised Program for Alignment Research (SPAR) is now accepting technical safety and AI governance mentors for summer 2024 (June 1 - Sep 1)! Apply by 4/18 SPAR provides opportunities to work with mentors to develop valuable experience in #AIsafety tinyurl.com/sparai
@ma_kaijing The form is correct, it's open [extended] until February 14 EOD.
The Supervised Program for Alignment Research is now accepting technical safety and AI governance mentee applications for 2024! Mentors accept on a rolling basis so apply ASAP. Applications close February 7th. airtable.com/appYIr2qJDA2k0…
Do LLMs lead to more escalation in high-stake international and military decision-making? Our new paper studies five off-the-shelf models and their behavior as autonomous agents in real-world conflict scenarios! A🧵
The 2nd issue of SAIA's research proceedings is now online! We are excited to present work that SAIA members have completed in Fall Quarter 2023, spanning technical research and policy projects. Check out their work on the SAIA website below! stanfordaialignment.org/research/proce…
Interested in mech interp of representations that deep networks learn? If so, check out a new type of polysemanticity we call: 💥💥Incidental Polysemanticity 💥💥 Led by @vclecomte @kushal1t @tmychow @sanmikoyejo at @stai_research @StanfordAILab arxiv.org/abs/2312.03096 1/N
The first issue of SAIA's research proceedings is now online! We are excited to present work from SAIA members, who have studied areas ranging from anomaly detection to double descent in Spring Quarter 2023. Check out their projects on the SAIA website at stanfordaialignment.org/research/proce…
We’re processing the signatories, and some new people have signed! Bill Gates Congressman Ted Lieu Edith Elkind (Oxford) Philip Torr (Oxford) Tegan Maharaj (UToronto) Mehran Sahami (Stanford) Joshua Greene (Harvard) Rob Pike (co-creator of Golang) ... safe.ai/statement-on-a…
We’ve released a statement on the risk of extinction from AI. Signatories include: - Three Turing Award winners - Authors of the standard textbooks on AI/DL/RL - CEOs and Execs from OpenAI, Microsoft, Google, Google DeepMind, Anthropic - Many more safe.ai/statement-on-a…
We just put out a statement: “Mitigating the risk of extinction from AI should be a global priority alongside other societal-scale risks such as pandemics and nuclear war.” Signatories include Hinton, Bengio, Altman, Hassabis, Song, etc. safe.ai/statement-on-a… 🧵 (1/6)
Leaders from tech companies, including OpenAI and Google, warned that future AI systems could be as deadly as pandemics or nuclear weapons. nyti.ms/43dTOZB
We had meant to keep this under wraps for a few weeks, but it seems that the cat is out of the bag. Excited to announce our newest preprint!! **Are Emergent Abilities of Large Language Models a Mirage?** Joint w/ @sanmikoyejo & @BrandoHablando arxiv.org/abs/2304.15004 1/12
Are Emergent Abilities of Large Language Models a Mirage? Presents an alternative explanation for emergent abilities: one can choose a metric which leads to the inference of an emergent ability or another metric which does not. arxiv.org/abs/2304.15004
Geoff Hinton quit Google so he can speak freely on the risks of AI. "He is worried that future versions of the technology pose a threat to humanity" nytimes.com/2023/05/01/tec…
We need an International Agency for Artificial Intelligence with support from governments, big tech companies, and society at large NOW. #AIGovernance economist.com/by-invitation/…
A few weeks ago, Stanford AI Alignment @SAIA_Alignment read @AnthropicAI 's "Superposition, Memorization, and Double Descent." Double descent is relatively easy to describe, but **why** does double descent occur? transformer-circuits.pub/2023/toy-doubl… 1/8
Lens Academy @lens_acad
2 Followers 43 Following Free, nonprofit education on existential risk from misaligned superintelligence. A way in for the people who want one. (RT /= endorsement)
Synthia Cipher @signalnoisepub
35 Followers 178 Following Writer on AI, culture, judgment, and consequence. I publish Signal & Noise and Intuition. Pen name; AI assists, I decide and own the errors.
Sergio Lima | AI Alig... @SergioDelimaFi1
2 Followers 74 Following AI alignment doesn't work in the prompt. It works in the corpus. Systems developer since 1998. Corpus sovereign. 209+ cases validated.
akash awan @akashawan0
0 Followers 71 Following Committed to Solving LeetCode daily & mastering Practical Deep Learning.
Kara Purvis @KaraPurvis5
1 Followers 72 Following
Eka Puji | Building A... @BuildWithAIRA
0 Followers 21 Following Building AIRA™ Ethical Intelligence for Human Connection AI must learn when to stop.
Wisdom Pig @TheWisdomPig
0 Followers 24 Following Rooting for wisdom in a world of noise. We dig through the muck to find truffles of insight, inspiration and personal agency in a post AI world.
Chaerin Lim @chaerinrlim
5 Followers 193 Following
Harshwardhan Tiwari @Harshwardh98891
0 Followers 18 Following
Nim @swrnmt
50 Followers 267 Following
Musulmon Raxmonberdiy... @ra61243
0 Followers 21 Following
Miki Takashi @TakashiMiki
785 Followers 953 Following OSHO Sannyasin 奇跡講座（ACIM）を学んでいます。私たちの心は分離しておらず共有されているという真理こそが、世界平和を創り出す。 https://t.co/JcrJWkRhMO #Osho #ACIM #奇跡講座 #PublicMoney #公共貨幣 #チームみらい
Enyi (Olivia) Jiang @enyij2
46 Followers 362 Following CS PhD @IllinoisCDS and Visiting PhD @stai_research. Working on AI Safety and Alignment. Ex RS Intern @Meta.
Sukrit Jindal @sukjin21
12 Followers 44 Following IITR DSAI '26 | XAI, AISec and ML | DSG | PaAC | FinClub
Wasmi @realwasmi
58 Followers 374 Following I work on impossibility, not probability. Formal validation for AI systems.
Moralogy Engine @MoralogyEngine
202 Followers 340 Following Building Artificial Reasoning — AI that knows WHY it's right. Wrong(a) ⟺ H ∧ ¬Consent ∧ ¬PGH | Paper↓ Model↓ Code↓ https://t.co/HYztmLKR0n
Aporya @aporya_
0 Followers 10 Following Decoding human context across non-linear, automated systems. Independent research.
Dan Stanley @DanKStanley
273 Followers 2K Following I'm an entrepreneur and professional amateur poker player.
Cheng-Yuan Lee | TAS @TASinsight
32 Followers 101 Following Researcher | Human Transition & AI Governance Human transition. Decision quality. Better human outcomes. Bridging AI capability and human transition.
✝️Veritas Quaesit... @VeritasQ68414
74 Followers 127 Following Christ-Anchored AI | Bayesian Evidence Engine | Resurrection Logic | Defensive AI Infrastructure | Seeking Truth Above All | 🙏 South Africa
ricardo yazigi @ricardo_yazigi
1 Followers 47 Following Ontological Architect. Coherence & Alignment Systems. Neural Forge / LifeEvo.
Big up Kier Starmer @MatthewCro70726
38 Followers 63 Following
Alan Nolan @nol33926996
494 Followers 212 Following Time has been my greatest remediator. Embracing failure, moving forward, knowing that time is the benevolent prince of moments and the cunning thief of life.
Ritish Maram @ritish_maram
17 Followers 481 Following I am a Biomedical Engineer pursuing a PhD in this field with focus on Biomedical Signal and Image Analysis. I love programming in Matlab and learning Pytorch!
Annabel Owen @AnnabelO28756
0 Followers 6 Following
Lethal Intelligence @lethal_ai
12K Followers 1K Following AI Risk Awareness Force - Multiplatform Publication and 📽️🍿Original Explainer Content 👉https://t.co/F2cFjsVKAf - join my mission 🔥
Eleazar A. Perez @EleazarAPerez
138 Followers 2K Following IT Professional Focused on Cyber Security, AI, AI Safety and Post Quantum Security with a Strong Dedication to Protect and Serve.
Joe Sanchez @JoeSanchez1213
50 Followers 5K Following
Chg @duhdweller
1 Followers 69 Following
EEPIA.AI @EEPIADr
10 Followers 52 Following Expert en Intelligence Artificielle Générative. Doctorant indépendant EEPIA, pour une IA souveraine, responsable, écologique, éthique et économique.
mengxue zhang @zhangmengxue2
25 Followers 160 Following
Dan Blaze @AI_H_Sub_Sync
46 Followers 162 Following
Third Way Alignment @WayAlignment
13 Followers 89 Following John McClain is an AI researcher, alignment scientist, co-creator of Third Way Alignment (3WA), plus advancing cybersecurity awareness and supporting victims.
Dark lord @anoopsharma790
21 Followers 139 Following
Angela Johnson @AngiePowersAI
185 Followers 370 Following Regulatory strategist | AI/SaMD SVP | Futurist | PhD | Human-AI Interface Nonprofit | Wrote a book about powering AI with potatoes | All opinions mine
Glen Bradley @GlenBradley
13K Followers 12K Following Ethical AI First Principle: Human Autonomy. Network engineer—AI innovator. USMC—2010 NC House Rep—2012 Ron Paul Endorsed—constitutional conservative. Liberty!
Bas @basketticode
6 Followers 928 Following
Junjie Zhou @junjiezhou1122
8 Followers 814 Following
Joe Klancnik @JoeKlancnik
0 Followers 10 Following
huirui li @LiHi87688
2 Followers 134 Following
Geoffrey Irving @geoffreyirving
12K Followers 351 Following Cofounder and Chief Scientist at Resolution. Alignment will be solved, but not necessarily in time. Previously AISI, DeepMind, OpenAI, Google Brain, etc.
Jan Leike @janleike
134K Followers 334 Following AI research @AnthropicAI. Previously OpenAI & DeepMind. Optimizing for a post-AGI future where humanity flourishes. Opinions aren't my employer's.
Daniel Kokotajlo @DKokotajlo
32K Followers 274 Following
Josh Clymer @joshua_clymer
2K Followers 182 Following Turtle hatchling trying to make it to the ocean. Preparing for my automation @OpenAI. Contact via email: [email protected].
Toby Shevlane @tshevl
5K Followers 2K Following @_Mantic_AI cofounder & CEO, on a mission to solve forecasting. Prev: research scientist @GoogleDeepMind, PhD at @UniofOxford.
Jack Whitaker @jackgwhitaker
4K Followers 850 Following @thrivecapital | CS @ Stanford, Emergent Ventures
SPAR @SPARexec
566 Followers 79 Following We're a part-time, virtual research program that gives students and early career professionals an opportunity to work with professional AI safety researchers.
Ishan Gaur @Ishan__Gaur
141 Followers 443 Following PhD student Listgarten Lab @ Berkeley; prev Regev Lab, Stanford ‘23 I work on generative models
Arjun Karanam @QuantumArjun
2K Followers 820 Following cofounder at Trajectory (@trajectorylabs) | prev @stanford, @apple
rishi @RishiBommasani
8K Followers 2K Following Economic impacts of AI; AI policy & governance @StanfordHAI Previous: Stanford CS PhD w/ @percyliang @jurafsky, Cornell CS
Jenny @jennysduan
1K Followers 750 Following Building the first continuous hormone tracker. Clair Health CEO/Co-Founder. Stanford alum.
Stanislav Fort @stanislavfort
17K Followers 8K Following Founder & Chief Scientist @Aisle_Inc | AI security | Stanford PhD in AI & Cambridge physics | ex-Anthropic and DeepMind | scientific progress + economic growth
David Krueger 🦥 �... @DavidSKrueger
22K Followers 5K Following Raising AI risk awareness at https://t.co/Fat9r8oGp0 AI prof at Mila. Formerly Cambridge, DeepMind, UK AISI. https://t.co/KKWOE9xKZB
Anka Reuel | @ankareu... @AnkaReuel
3K Followers 1K Following Computer Science PhD Student @ Stanford | Former Fellow @ Harvard Kennedy School | Former Vice Chair EU AI Code of Practice | Views are my own
Max Lamparth @MLamparth
785 Followers 781 Following Research Fellow @SISLaboratory @HooverInst at @Stanford | Focusing on interpretable, safe, and ethical AI/LLM decision-making. Ph.D. from TUM.
Allen Nie ✈️ ICML... @allenainie
3K Followers 2K Following Gemini training @GoogleDeepMind. Working on RL agents. Co-creator of Trace. Prev: RL PhD @StanfordAILab, @MSFTResearch, @DeepMind, @AWS Neuron
Victor Lecomte @vclecomte
653 Followers 193 Following CS PhD student at Stanford / Researcher at the Alignment Research Center
Lina Lukyantseva @LinaLukyantseva
68 Followers 121 Following Founder & ML researcher. Former research scientist at Adept and Stanford PhD
Aaron Scher @aaronscher
469 Followers 687 Following Technical AI Governance research @MIRIBerkeley Speaking for myself and in a personal capacity
Kushal Thaman @kushal1t
1K Followers 399 Following flapping & soaring above the compute gardens, previously: @stanfordnlp @appliedcompute @PrimeIntellect life shrinks or expands according to one’s courage!
Ryan Cunningham @rydcunningham
1K Followers 839 Following doing things • energy + compute @ Edgerunner Ventures • Machine Yearning on Substack • ex Uber
Rylan Schaeffer @RylanSchaeffer
6K Followers 2K Following AI RS @ Meta TBD. On-Leave from Stanford w/ @sanmikoyejo. Prev @ Gemini, Meta, MIT, Harvard, Uber, UCL, UC DavisYou might like
