←
Principles of Intelligence (PrincInt)162 posts
Principles of Intelligence (PrincInt) avatar✓

Principles of Intelligence (PrincInt) ✓

@PrincInt

We study intelligent behavior across a broad range of contexts to build the foundational understanding required to create aligned AI systems. Formerly PIBBSS.

◷ Joined December 2021▧ 4 Photos and videos
Iliad avatar
⟳ Principles of Intelligence (PrincInt) retweeted
Iliad@Iliad_research·Nov 17

7.5 hours left to apply to the Iliad January Intensive and Fellowship!

Post attachment
AlignmentJournal avatar
⟳ Principles of Intelligence (PrincInt) retweeted
AlignmentJournal@AlignmentJrnl·Nov 16

The Alignment Journal is looking for reviewers for "Ecology of Self-Replicating AI Agents: Collaboration Creates a Population Threshold for Takeoff". You might be interested if you have experience with population dynamics, AI cyber capability or self-replication evals, multi-agent scaling, or malware and botnet spread models. Authors stay anonymous while the paper is under review. Reviewers are paid, with a bonus for being early. Nominate yourself ⬇️

Post attachment
AlignmentJournal avatar
⟳ Principles of Intelligence (PrincInt) retweeted
AlignmentJournal@AlignmentJrnl·Nov 12

Now under review at the Alignment Journal: “General Agents Contain World Models, even under Partial Observability and Stochasticity”. Reviewers for this paper have been found. To review in the future, make an account on our website and list your expertise. Editors will search among the accounts when recruiting reviewers for new papers. You can also nominate yourself.

Post attachment
AlignmentJournal avatar
⟳ Principles of Intelligence (PrincInt) retweeted
AlignmentJournal@AlignmentJrnl·Oct 22

The Alignment Journal publishes research on the scientific foundations of understanding, predicting, and steering artificial intelligent systems. As of today, submissions are open to everyone. What we do differently: - We pay reviewers, with bonuses for speed and insight. - Review discussion is confidential, but every accepted paper is published with a “review summary” to distill the insights generated. - Each paper is judged against our acceptance bar, not against other submissions. - Papers under review are listed publicly, and researchers can nominate themselves to review, so each paper can reach the reviewers who know the topic best. We seek work that builds theoretical or otherwise principled analyses of agency, robustness, incentives, interpretability, generalization, and long-term behavior, and whose significance survives the deletion of any particular model, dataset or benchmark. Empirical investigations of such ideas are welcome, and negative results are encouraged. We are especially interested in approaches that could apply to future superintelligent systems that interact and self-improve. You can submit your preprint in any format. Submissions are rolling and open now on the website. If you are instead interested in reviewing or serving as an action editor (basically: an area chair), create an account on our website. Links to submit, our scope and the reasoning behind the Journal are in the reply ⬇️

Post attachment
Allison Duettmann avatar
⟳ Principles of Intelligence (PrincInt) retweeted
Allison Duettmann@allisondman·Oct 12

Vision Weekend @foresightinst 40th Speaker Sneak Peek Secure, Sovereign & Resilient AI +@woj_zaremba, OpenAI Foundation +@ilblackdragon, NEAR Protocol +@sebkrier , Google DeepMind + Jenny Read, ARIA +@NicoleOzer, Electronic Frontier Foundation Neuro AI & AI for Neuro +@SumnerLN, Merge + Matthew MacDougall, Neuralink +@maxhodak_ , Science Corporation +@JoanneZPeng, Amaranth Foundation +@AdamMarblestone, Convergent Research +@Matt_R_Angle, Paradromics Life Unlimited: Biotech & Biosecurity +@thekaransinghal, OpenAI +@mattkrisiloff, Conception Bio + @hannu, Red Queen Bio +@velychko_s, Harvard University Nano, Energy & Space + Ralph Merkle, Institute for Molecular Manufacturing +Ivan Jayapurna, ARIA +@schingler, Planet Labs +@erika_alden_d, Pioneer Labs + @ltelkins, UC Berkeley Space Sciences Lab For Profit Funding Paradigms +@v_maini, Mythos +@zweinberg, Ex Ante +@_mattmandel, Cosmos Ventures Nonprofit Funding Paradigms +@nanransohoff, Frontier Climate +@rohan_subramani, Coefficient Giving +@seemaychou, Astera Institute, Navigation Fund +@tkalil2050, RenPhil Existential Hope+ + @mattbotvinick, Anthropic +@RosieCampbell, Eleos AI Research +@PracheeAC, Astera Institute +@robinhanson, George Mason University +@gladstein, Human Rights Foundation + Anti debate with @Liv_Boeree + Office hours with our favorite orgs, @AsimovPress, @BuckInstitute, @BlueDotImpact, @activatefellows, @farairesearch, @collect_intel, @Spec__Tech, @JoinEdgeCity, @LBF_org, @PrincInt, @TheIHS, and more. + Sci-fi book swap, unconference, pitch competition, tech demos, anniversary festivities, tea social, and more. + Speaker & Sponsor Gatherings like pre-party aboard the USS Hornet aircraft carrier, lab tours at @E11BIO, @LongshotSpace, CalWave,@ScienceCorp_, Dolphin Labs, plus a Foresight 40th Anniversary Soiree. It's hard to overstate how excited I am for this weekend celebrating futures of Existential Hope unlocked by science and technology. Thanks to our partners for making this event possible @protocollabs, @paradromics, @RetroBio_, @eigenlabs, @FUTO_Tech, @d_model_ai Event page & tickets: foresight.org/events/vision-…

0:46