korrents

On the map

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

← Self-play as it was done in the past is too narrow: it only ever…

17 connected korrents · 15 moments from 24 May 2017 to 17 Oct 2026.

Everything filed under AI agents AI agents Everything filed under reinforcement learning reinforcement learning Everything filed under mental models mental models Everything filed under video games video games Everything filed under coding agents coding agents Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Self-play as it was done in the past is too narrow: it only ever develops a small set of skills like negotiation and strategising. Self-play as it was done in the past istoo narrow: it only ever develops a smallset of skills like negotiation andstrategising. Last stated 12 months ago 25 Nov 2025 IS Ilya Sutskever — holds since 2025-11-25 — tap for who they are Same subject: Playing games where others have the aptitudes and one does not is close to certain to lose, so one has to find where one has an edge and stay inside one’s circle of competence — tap to centre the map on it Playing games where others have theaptitudes and one does not is closeto certain to lose, so one has tofind where one has an edge and stayinside one’s circle of competence CM Charlie Munger — holds since c. 1994 — 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: Agents are good at managing orchestration on their own — tap to centre the map on it Agents are good at managingorchestration on their own Last stated a month ago 15 Oct 2026 KD Kent C. Dodds — holds since 2026-10-15 — tap for who they are Same subject: Making character skills matter more adds dynamism and variation to a game. — tap to centre the map on it Making character skills matter moreadds dynamism and variation to agame. Last stated 9 years ago 24 May 2017 TS Tynan Sylvester — holds since 2017-05-24 — tap for who they are Same subject: You cannot know what a program should do until you play with it, so in the agentic age you should be as vague as you can up front and then interact with what appears. — tap to centre the map on it You cannot know what a programshould do until you play with it, soin the agentic age you should be asvague as you can up front and theninteract with what appears. Last stated 3 months ago 26 Aug 2026 DH David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are Same subject: Working alone with agents may be efficient, but it means people stop learning from each other. — tap to centre the map on it Working alone with agents may beefficient, but it means people stoplearning from each other. Last stated 2 months ago 10 Sept 2026 KS Karri Saarinen — holds since 2026-09-10 — 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: Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. — tap to centre the map on it Capability does not generalise forfree: a model that will movemountains on an agentic task stilltells the same bad joke it told fiveyears ago. Last stated 8 months ago 20 Mar 2026 AK Andrej Karpathy — holds since 2026-03-20 — tap for who they are Same subject: A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. — tap to centre the map on it A feedback loop that reinforces abehavior pulls it toward whateverimproves the loop's own score. Last stated 3 months ago 26 Aug 2026 HK Henrik Karlsson — holds since 2026-08-26 — 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: Behaviours like massively deluding humans or trying to seize control of assets could in principle generalise from reward hacking. — tap to centre the map on it Behaviours like massively deludinghumans or trying to seize control ofassets could in principle generalisefrom reward hacking. Last stated a year ago 8 Jul 2025 RG Ryan Greenblatt — holds since 2025-07-08 — tap for who they are Same subject: Current models are unsafe because they are not smart enough, not because they are too smart. — tap to centre the map on it Current models are unsafe becausethey are not smart enough, notbecause they are too smart. Last stated 2 months ago 13 Sept 2026 FC François Chollet — holds since 2026-09-13 — tap for who they are Same subject: How aligned current models are depends a lot on things like their degree of reward hacking. — tap to centre the map on it How aligned current models aredepends a lot on things like theirdegree of reward hacking. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — 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: Before training a base model with RL to emit think tokens, it is better to do some continued pre-training or supervised fine-tuning with those tokens present. — tap to centre the map on it Before training a base model with RLto emit think tokens, it is betterto do some continued pre-training orsupervised fine-tuning with thosetokens present. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: Distilling from a model's reasoning traces gets there quicker and cheaper than reinforcement learning, which is why labs that invest in RL complain about it. — tap to centre the map on it Distilling from a model's reasoningtraces gets there quicker andcheaper than reinforcement learning,which is why labs that invest in RLcomplain about it. Last stated a month ago 17 Oct 2026 SR Sebastian Raschka — holds since 2026-10-17 — 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 Self-play as it was done in the past is too narrow: it only ever develops a small set of skills like negotiation and strategising. Last stated 25 Nov 2025 · 12 months ago Holds Ilya Sutskever Read this korrent →