Ryan Kidd
@ryan_kidd44
Followers
2K
Following
8K
Media
27
Statuses
1K
Co-Executive Director @MATSprogram, Co-Founder @LondonSafeAI, Regrantor @Manifund | PhD in physics | Accelerate AI alignment + build a better future for all
Berkeley, CA
Joined March 2019
RT @farairesearch: 1/."Swiss cheese security", stacking layers of imperfect defenses, is a key part of AI companies' plans to safeguard mod….
0
14
0
RT @americans4ri: The moratorium just got taken out of the budget bill in a LANDSLIDE vote. 99 to 1. Incredible. Thank you to the lawmaker….
0
98
0
RT @Research_FRI: Our new study finds: recent AI capabilities could increase the risk of a human-caused epidemic by 2-5x, according to 46 b….
0
19
0
Fermionic moral theories value new moral patients only insofar as they have different experiences. "Moral degeneracy pressure" would disfavor the creation of identical copies, as they would be treated like "pointers" to the original, rather than independent moral patients. Under.
2
0
11
Bosonic moral theories value multiple copies of the same moral patient experiencing identical states, like perfect bliss. Under these theories, "tiling the universe in hedonium" is permissible, because new copies experiencing the same qualia have nonzero moral value. A "bosonic.
1
0
9
I propose a new name for an important metaethical distinction: bosonic vs. fermionic moral theories. Bosons are particles that can degenerately occupy the same state, while fermions can only occupy individual states.
2
1
16
RT @eli_lifland: Since AI 2027 people have often asked us what they can do to make AGI go well. I've just published a blog post covering:.(….
0
44
0
RT @TomDavidsonX: To quickly transform the world, it's not enough for AI to become super smart (the "intelligence explosion"). AI will also….
0
15
0
RT @peterwildeford: Meet the podcast episode that singlehandedly added a year to my AGI timelines. Here are my notes 👇on this amazing podc….
0
26
0
Sometimes it feels like there is a deep loneliness and anxiety at the heart of the East Bay EA, Rationality, Postrat, Tpot social scene. Like people are afraid to put down roots or truly connect. because it could all be snatched away.
0
0
10
Technical AI alignment/control is still impactful; don't go all-in on AI gov!.- Liability incentivises safeguards, even absent regulation;.- Cheaper, more effective safeguards make it easier for labs to meet safety standards;.- Concrete safeguards give regulation teeth.
6
5
48
RT @geoffreyirving: New alignment theory paper! We present a new scalable oversight protocol (prover-estimator debate) and a proof that hon….
0
55
0
RT @Yoshua_Bengio: The @EU_Commission is setting up a scientific panel of 60 independent experts to support the implementation and enforcem….
0
25
0
RT @robertwiblin: Ben Todd has written the best thing on how to plan your career given AI/AGI. Will thread. A very plausible scenario is s….
0
143
0
RT @Scott_R_Singer: Over the last year, those of us who follow China's AI governance have been carefully watching whether China would estab….
0
109
0
RT @OwainEvans_UK: Our new paper: Emergent misalignment extends to *reasoning* LLMs. Training on narrow harmful tasks causes broad misalign….
0
57
0
Amazing! So excited to have supported this work @MATSprogram.
1/8: The Emergent Misalignment paper showed LLMs trained on insecure code then want to enslave humanity. ?!. We're releasing two papers exploring why! We:.- Open source small clean EM models.- Show EM is driven by a single evil vector.- Show EM has a mechanistic phase transition
0
0
9
Update: it looks like 71% of mentor applicants are above our excellence bar and we will likely accept ~28% of all mentor applicants. For comparison, the acceptance rate for scholars in MATS 2.0 was 33%!.
0
0
1
Excited to have supported this research @MATSprogram !.
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) 🧵
0
0
7