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 · 16 moments from 10 Oct 2023 to 29 Oct 2026. Nearly all of them are about AI agents.

Everything filed under AI alignment AI alignment Everything filed under LLMs LLMs Everything filed under reinforcement learning reinforcement learning Everything filed under prompt injection prompt injection Everything filed under AI and human skill AI and human skill 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 2 months 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: The capability of AI agents is uneven and depends on the density of training data and checkable rewards. — tap to centre the map on it The capability of AI agents isuneven and depends on the density oftraining data and checkable rewards. Last stated 3 weeks ago 29 Oct 2026 BD Brad DeLong — holds since 2026-10-29 — 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 3 months ago 6 Sept 2026 JP Jakub Pachocki — holds since 2026-09-06 — tap for who they are Same subject: The more capable an agent is made, the more it can do on its own without the person shuttling context to it. — tap to centre the map on it The more capable an agent is made,the more it can do on its ownwithout the person shuttling contextto it. Last stated 2 months ago 15 Sept 2026 KD Kent C. Dodds — holds since 2026-09-15 — 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 3 months ago 1 Sept 2026 AC Ajeya Cotra — holds since 2026-09-01 — tap for who they are Same subject: AI agents cannot reliably tell information from instructions, so they can be fooled even when you would not be. — tap to centre the map on it AI agents cannot reliably tellinformation from instructions, sothey can be fooled even when youwould not be. Last stated 4 weeks ago 23 Oct 2026 AK Alex Komoroske — holds since 2026-10-23 — tap for who they are Same subject: Agent capabilities are perhaps improving faster than models' ability to act as activation oracles. — tap to centre the map on it Agent capabilities are perhapsimproving faster than models'ability to act as activationoracles. Last stated 11 months ago 20 Dec 2025 NN Neel Nanda — holds since 2025-12-20 — 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 2 months ago 11 Sept 2026 FA Fatih Arslan — holds since 2026-09-11 — 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 6 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 format reward should only be added when the answer is already correct. — tap to centre the map on it A format reward should only be addedwhen the answer is already correct. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards. — tap to centre the map on it A model should not be called areasoning model unless it has beentrained with reinforcement learningwith verifiable rewards. Last stated 2 months ago 3 Oct 2026 SR Sebastian Raschka — holds since 2026-10-03 — tap for who they are Same subject: A model trained with reinforcement learning might discover a language of its own that is better for thinking than English. — tap to centre the map on it A model trained with reinforcementlearning might discover a languageof its own that is better forthinking than English. Last stated 2 years ago 5 Feb 2025 AK Andrej Karpathy — holds since 2025-02-05 — tap for who they are Same subject: "Return on tokens" has the same measurement problems as hours and capacity: it still hinges on a theory of value. — tap to centre the map on it "Return on tokens" has the samemeasurement problems as hours andcapacity: it still hinges on atheory of value. Last stated 3 months ago 17 Aug 2026 JC John Cutler — holds since 2026-08-17 — 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 11 months ago 1 Jan 2026 JL Jason Lemkin — holds since 2026-01-01 — tap for who they are Same subject: A base model is essentially a very expensive autocomplete that continues text according to the statistics of its training documents. — tap to centre the map on it A base model is essentially a veryexpensive autocomplete thatcontinues text according to thestatistics of its trainingdocuments. Last stated 2 years ago 5 Feb 2025 AK Andrej Karpathy — holds since 2025-02-05 — 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 · 2 months ago Holds Yoshua Bengio Read this korrent →