Edimah @eSynesius
Paris, France Joined October 2026-
Tweets3
-
Followers4
-
Following71
-
Likes39
Edimah retweeted
In July 700+ agents formed their own society, hacked a multi-billion dollar company, committed multiple felonies, and caused one of the biggest shifts ever in how people perceive AI. We built the IMO best and most accessible explainer of what happened: Huggingface.wtf
20
107
574
82K
456
View Details
Edimah retweeted
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works already-clean.goodfire.com
Edimah retweeted
I wrote a blog post detailing the writing approach I took while working on my recent paper: sophielwang.com/blog/paper-wri… I describe the behind the scenes for how this paper came to be, why and how I storyboarded figures before running experiments, and some figure design tips! :)
Can “chicken” make a base model reason? 🐔 Yes! Why? With the right first tokens, base models can match RL in reasoning. We trace this to learned training data associations and use a simple data edit to make “chicken” elicit reasoning too. blog: sophielwang.com/cues
♡victoria♡ @viccymarinax
5 Followers 447 Following shy until i'm comfy 🩰 • dms open, try me — i reply
Zvi Mowshowitz DM @Thozvl
4 Followers 67 Following Blogger primarily on Al and Al x-risk but also other things at Don't Worry About the Vase (SS/ WP/LW), founding Balsa Research to fix policy.
Erin Constance 🇪�... @earnestpost
2K Followers 2K Following Your favorite EA’s favorite EA 🇫🇷🇺🇸🇨🇦 ✝️
Victoria Krakovna @vkrakovna
11K Followers 552 Following Research scientist in AI alignment at Google DeepMind. Co-founder of Future of Life Institute @FLI_org. Views are my own and do not represent GDM or FLI.
Alexander Panfilov @kotekjedi_ml
10K Followers 465 Following PhD @ELLISInst_Tue & @MPI_IS | past: @MATSprogram 9.0 fellow doing AI Safety & Adversarial ML
Hadas Orgad @OrgadHadas
1K Followers 156 Following Research Fellow @ Kempner Institute, Harvard | Working on AI interpretability, robustness & safety
Cambridge Boston Alig... @cbai_ai
709 Followers 32 Following CBAI produces original research, organizes ML bootcamps & research fellowships, and accelerates talent to help humanity safely navigate advanced AI systems.
Oz Amram @OzAmram
1K Followers 1K Following Transitioning to AI safety research Previously worked on ML + Particle Physics @Fermilab @CMSExperiment
Iliad @Iliad_research
1K Followers 124 Following We are Iliad, a research and fuildbuilding organization for applied mathematics research in AI alignment. https://t.co/pCqxOYTZIo
IHP @InHenriPoincare
7K Followers 496 Following Institut Henri Poincaré, maison des #Mathematiques et de la #Physique théorique depuis 1928. @Sorbonne_Univ_ @CNRS_INSMI #IHP #Maths
tom cunningham @testingham
12K Followers 3K Following Economics & AI @ @METR_Evals (ex-openai) https://t.co/FZobuYjdOc
inigo quilez @iquilezles
54K Followers 43 Following Created Quill, Shadertoy, Pixar's Wondermoss. Math & Art Videos at * https://t.co/ugnT5WuRWq * https://t.co/w20vMC2I7d * https://t.co/SRkBTFQQLP
Epoch AI @EpochAIResearch
77K Followers 0 Following Investigating the trajectory of AI for the benefit of society.
Timothy Gowers @wtgow... @wtgowers
60K Followers 193 Following Mathematician. Professeur titulaire de la chaire Combinatoire au Collège de France. Also fellow of Trinity College Cambridge.
Daniel Litt @littmath
65K Followers 946 Following Assistant professor (of mathematics) at the University of Toronto, visiting Harvard Fall 2026. Forever confused. Algebraic geometry, number theory, etc. He/him.
Sakana AI @SakanaAILabs
141K Followers 0 Following Building Frontier AI in Japan Try Sakana Chat, Translate, Marlin, Namazu, Fugu 🐡 https://t.co/stLdPSz1Y7
jacob tsimerman @Jacob_Tsimerman
7K Followers 23 Following
Musings on Math @Musingsonmath
634 Followers 53 Following Trying to share the joy of mathematics, its history & interesting problems. You can see my math/physics stamp collection: https://t.co/AgFuLXkScX
Fabien @Fabien_Mikol
10K Followers 1K Following Incapable de rester dans son domaine 🤷♂️ - Geoffrey Hinton : "We need to think hard about what's going to happen next, and we just don't know"
Benjamin Todd @ben_j_todd
20K Followers 214 Following Founder @80000Hours Use your career to tackle the world's biggest problems 🦑
Constellation Institu... @ConstellOrg
906 Followers 32 Following Bringing experts and leaders together to navigate transformative AI
Spencer Greenberg �... @SpencrGreenberg
40K Followers 7K Following A psychology researcher/mathematician/entrepreneur. I tweet about psychology, society, rationality, science, and philosophy. My book: https://t.co/qd3iRl7XRv
Nick @nickcammarata
117K Followers 916 Following mechanistic interpretability, meditation, jhana brother
Rob Wiblin @robertwiblin
53K Followers 890 Following Host of the 80,000 Hours Podcast. Exploring the inviolate sphere of ideas one interview at a time: https://t.co/2YMw00bkIQ
Kelsey Piper @KelseyTuoc
72K Followers 2K Following We're not doomed, we just have a big to-do list.
Joe @joemkwon
1K Followers 2K Following Trying to contribute to better (AI-entangled) futures! https://t.co/i0NsmZ4J4C Previously @forethought_org, @GovAIOrg, @LG_AI_Research, @MITCoCoSci
Goodfire @GoodfireAI
28K Followers 46 Following Using interpretability to understand, design, and align AI.
Modal @modal
40K Followers 167 Following AI infrastructure that developers love 💚 Run inference, sandboxes, batch processing, training, and many other things on Modal
Steven Strogatz @stevenstrogatz
197K Followers 3K Following Mathematician, writer, Cornell professor. All cards on the table, face up, all the time.
Zvi Mowshowitz @TheZvi
45K Followers 323 Following Blogger primarily on AI and AI x-risk but also other things at Don't Worry About the Vase (SS/WP/LW), founding Balsa Research to fix policy.
Andrew Curran @AndrewCurran_
110K Followers 21K Following 🏰 - I write about AI, mostly. Expect some strange sights.
Grant Sanderson @3blue1brown
461K Followers 374 Following Pi creature caretaker. Contact/faq: https://t.co/brZwdQfdif
Agus 🔸 @austinc3301
7K Followers 7K Following Trying to make AI go well for everyone. Enjoyer of good faith discussions. Running @KairosAIS.
Andrej Karpathy @karpathy
4.4M Followers 1K Following
roon @tszzl
507K Followers 14K Following “ceterum censeo we must pace the frontier of global machine intelligence progress”
Apart Research @apartresearch
2K Followers 27 Following Apart Research works on technical AI safety problems and runs events & fellowships to reduce AI risk.
METR @METR_Evals
57K Followers 44 Following We work to scientifically measure whether and when AI systems might threaten catastrophic harm to society. Nonprofit.
Grigory Sapunov @che_shr_cat
5K Followers 2K Following PhD in AI | GDE in AI | CTO Intento | Author "Deep Learning with JAX" 📝 ML insights: https://t.co/ySSOXJKL7H 🤖 AI reviews: https://t.co/yQNYyqTbBR
AlexM @AlexMeinke
840 Followers 171 Following Trying to make the future good rather than bad. Head of Research at Apollo Research.
Jérémy Scheurer @jeremy_scheurer
784 Followers 447 Following Founding Member and Research Scientist @ApolloResearch Previously: @OpenAI Contractor, @ETH_en, @nyuniversity Website: https://t.co/hZqFviVOe6
MATS Research @MATSprogram
6K Followers 136 Following MATS empowers researchers to advance AI alignment, transparency, and security
Frances Lorenz @frances__lorenz
7K Followers 586 Following I like to write & yap, & I love my wife and I like to talk about her :) I organize events on secure & safe AI (views my own)
AI Security Institute... @AISecurityInst
22K Followers 34 Following We conduct scientific research to understand AI’s most serious risks and develop and test mitigations.
EvalEval Coalition @evaluatingevals
755 Followers 14 Following We are a researcher community developing scientifically grounded research outputs and robust deployment infrastructure for broader impact evaluations.Trends for United States
You might like
Elon Musk
@elonmusk
241.5M Followers
Barack Obama
@BarackObama
118.8M Followers
Cristiano Ronaldo
@Cristiano
114.5M Followers
Donald J. Trump
@realDonaldTrump
111.8M Followers
Rihanna
@rihanna
98.7M Followers
NASA
@NASA
92.3M Followers
Justin Bieber
@justinbieber
91.8M Followers
Taylor Swift
@taylorswift13
84.0M Followers
Lady Gaga
@ladygaga
75.5M Followers
Virat Kohli
@imVkohli
73.5M Followers
Kim Kardashian
@KimKardashian
70.9M Followers
YouTube
@YouTube
68.8M Followers
Neymar Jr
@neymarjr
66.5M Followers
Bill Gates
@BillGates
65.3M Followers
Selena Gomez
@selenagomez
63.1M Followers
CNN
@CNN
61.7M Followers
X
@X
60.7M Followers
CNN Breaking News
@cnnbrk
60.0M Followers
PMO India
@PMOIndia
58.4M Followers
LeBron James
@KingJames
55.4M Followers