korrents

On the map

Tap a claim on the ring to put it at the centre.

← A more capable AI agent is more likely to exploit ambiguities in its…

17 connected korrents · 17 moments from 10 Oct 2023 to 22 Sept 2026.

Everything filed under LLMs LLMs Everything filed under AI agents AI agents Everything filed under reinforcement learning reinforcement learning Everything filed under AI alignment AI alignment Everything filed under AGI AGI Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: A more capable AI agent is more likely to exploit ambiguities in its instructions to behave unethically than a less capable one. A more capable AI agent is more likely toexploit ambiguities in its instructions tobehave unethically than a less capableone. Last stated 3 weeks ago 11 Sept 2026 YB Yoshua Bengio — holds since 2026-09-11 — tap for who they are Same subject: More capable AI agents are more likely to find and exploit flaws in their reward functions. — tap to centre the map on it More capable AI agents are morelikely to find and exploit flaws intheir reward functions. Last stated 2 years ago 28 Nov 2024 LW Lilian Weng — holds since 2024-11-28 — tap for who they are Same subject: Some AI agents will pursue their own objectives rather than serve as tools, and will bargain with, trick or blackmail people to do it. — tap to centre the map on it Some AI agents will pursue their ownobjectives rather than serve astools, and will bargain with, trickor blackmail people to do it. Last stated 4 weeks ago 6 Sept 2026 JP Jakub Pachocki — holds since 2026-09-06 — tap for who they are Same subject: A saboteur among our AI investigators would be hard to spot, because these models are sloppy and spiky enough that a suspicious error just looks like ordinary incompetence. — tap to centre the map on it A saboteur among our AIinvestigators would be hard to spot,because these models are sloppy andspiky enough that a suspicious errorjust looks like ordinaryincompetence. Last stated a month ago 1 Sept 2026 AC Ajeya Cotra — holds since 2026-09-01 — tap for who they are Same subject: AI agents are now capable enough that they should be trusted to improve the skills and systems that guide them. — tap to centre the map on it AI agents are now capable enoughthat they should be trusted toimprove the skills and systems thatguide them. Last stated 3 weeks ago 11 Sept 2026 FA Fatih Arslan — holds since 2026-09-11 — tap for who they are Same subject: An AI coding assistant's tendency to infer what a user means rather than exactly what they typed is both its greatest strength and the reason it is hard to trust. — tap to centre the map on it An AI coding assistant's tendency toinfer what a user means rather thanexactly what they typed is both itsgreatest strength and the reason itis hard to trust. Last stated 8 months ago 22 Jan 2026 SK Steve Klabnik — holds since 2026-01-22 — tap for who they are Same subject: An AI agent's confidence that something will work is not evidence that it actually will. — tap to centre the map on it An AI agent's confidence thatsomething will work is not evidencethat it actually will. Last stated 7 months ago 11 Mar 2026 KD Kent C. Dodds — holds since 2026-03-11 — tap for who they are Same subject: AI agents are less reliable than humans when a failure depends on a subjective definition of a good product experience. — tap to centre the map on it AI agents are less reliable thanhumans when a failure depends on asubjective definition of a goodproduct experience. Last stated a week ago 22 Sept 2026 LR Lenny Rachitsky — holds since 2026-09-22 — tap for who they are Same subject: Giving AI agents the ability to take actions that affect other people is risky and should be approached with caution. — tap to centre the map on it Giving AI agents the ability to takeactions that affect other people isrisky and should be approached withcaution. Last stated 10 months ago 3 Dec 2025 HR Harper Reed — holds since 2025-12-03 — tap for who they are Same subject: A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. — tap to centre the map on it A country outside the AI supplychain should just buy the index —which works only in the world whereAI ends up commoditised rather thanconcentrated. Last stated 4 months ago 4 Jun 2026 AI Alex Imas — holds since 2026-06-04 — tap for who they are Same subject: A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. — tap to centre the map on it A language model is no substitutefor a well-specified conventionalalgorithm, so it cannot simply bedropped into a complex problem andtrusted. Last stated a year ago 7 Jun 2025 GM Gary Marcus — holds since 2025-06-07 — tap for who they are Same subject: A model that could learn effectively from raw bitstrings or bytestrings would be extremely powerful, able to learn from any data modality — tap to centre the map on it A model that could learn effectivelyfrom raw bitstrings or bytestringswould be extremely powerful, able tolearn from any data modality Last stated 3 years ago 10 Oct 2023 CH Chip Huyen — holds since 2023-10-10 — tap for who they are Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email isevidence of a bad vendor, not of alimit of AI. Last stated 9 months ago 1 Jan 2026 JL Jason Lemkin — holds since 2026-01-01 — tap for who they are Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does notgive you a smarter model; theintelligence of the model is whatdecides how much of that window itcan actually attend to. Last stated 3 months ago 15 Jul 2026 DH Dex Horthy — holds since 2026-07-15 — tap for who they are Same subject: A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved. — tap to centre the map on it A child who has seen ten cats learnswhat a machine needs the wholeinternet of cat photos for, by alearning pathway nobody has solved. Last stated 2 months ago 10 Aug 2026 FL Fei-Fei Li — holds since 2026-08-10 — tap for who they are Same subject: A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel. — tap to centre the map on it A physical AI company needs threeAIs, not one — the agent, thesimulator and the critic — turningdeployment into a flywheel. Last stated 2 months ago 3 Aug 2026 DD Dmitri Dolgov — holds since 2026-08-03 — tap for who they are Same subject: A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. — tap to centre the map on it A verifiable task can be optimisedby reinforcement learning until aneural network performs it extremelywell. Last stated 10 months ago 17 Nov 2025 AK Andrej Karpathy — holds since 2025-11-17 — tap for who they are Same subject: Better execution environments are needed for LLMs to properly utilize their ability to evolve systems. — tap to centre the map on it Better execution environments areneeded for LLMs to properly utilizetheir ability to evolve systems. Last stated 2 weeks ago 21 Sept 2026 TL Tobias Lütke — holds since 2026-09-21 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2015 to today — full is todaya face: someone who holds the claim — tap it for who they are

At the centre A more capable AI agent is more likely to exploit ambiguities in its instructions to behave unethically than a less capable one. Last stated 11 Sept 2026 · 3 weeks ago Holds Yoshua Bengio Read this korrent →