korrents

On the map

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

← Humans have a million times better sample efficiency than AI.

17 connected korrents · 18 moments from 5 Nov 2019 to 14 Nov 2026.

Everything filed under measuring intelligence measuring intelligence Everything filed under LLMs LLMs Everything filed under ARC-AGI ARC-AGI Everything filed under AGI AGI Everything filed under creativity creativity Everything filed under optimism optimism Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Humans have a million times better sample efficiency than AI. Humans have a million times better sampleefficiency than AI. Last stated a week ago 14 Nov 2026 NS Noah Smith — holds since 2026-11-14 — tap for who they are Same subject: Current AI models are significantly less sample efficient than humans. — tap to centre the map on it Current AI models are significantlyless sample efficient than humans. Last stated 5 months ago 19 Jun 2026 DP Dwarkesh Patel — holds since 2026-06-19 — tap for who they are Same subject: AI systems are better than humans at coordinating with each other, and they move much faster than humans do. — tap to centre the map on it AI systems are better than humans atcoordinating with each other, andthey move much faster than humansdo. Last stated 3 months ago 31 Aug 2026 JC Jack Clark — holds since 2026-08-31 — tap for who they are Same subject: Whenever AI can do something as well as or better than humans, that thing arguably stops being valuable or special. — tap to centre the map on it Whenever AI can do something as wellas or better than humans, that thingarguably stops being valuable orspecial. Last stated 2 months ago 28 Sept 2026 PL Pieter Levels — holds since 2026-09-28 — tap for who they are Same subject: AI is going to be able to do everything humans can do, and in some cases already does it better. — tap to centre the map on it AI is going to be able to doeverything humans can do, and insome cases already does it better. Last stated 3 months ago 23 Aug 2026 DS David Senra — holds since 2026-08-23 — tap for who they are Same subject: AI excels at certain tasks but cannot substitute for human thinking. — tap to centre the map on it AI excels at certain tasks butcannot substitute for humanthinking. Last stated 3 months ago 1 Sept 2026 NM Nick Maggiulli — holds since 2026-09-01 — tap for who they are Same subject: Current AI models still fall short of expert human performance. — tap to centre the map on it Current AI models still fall shortof expert human performance. Last stated 2 years ago 27 Jan 2025 NE Nelson Elhage — holds since 2025-01-27 — tap for who they are Same subject: AI systems are much better at tasks whose correctness can be verified than at tasks whose correctness cannot be checked. — tap to centre the map on it AI systems are much better at taskswhose correctness can be verifiedthan at tasks whose correctnesscannot be checked. Last stated 4 months ago 13 Jul 2026 AN Arvind Narayanan — holds since 2026-07-13 — tap for who they are Same subject: AI will be more creative than humans — tap to centre the map on it AI will be more creative than humans Last stated 4 years ago 5 Dec 2022 DH David Heinemeier Hansson — holds since 2022-12-05 — tap for who they are Same subject: A unit of measure needs defining, perhaps via a chain of increasingly hard problems, each pair of which a single model can solve. — tap to centre the map on it A unit of measure needs defining,perhaps via a chain of increasinglyhard problems, each pair of which asingle model can solve. Last stated 2 months ago 15 Sept 2026 PG Paul Graham — holds since 2026-09-15 — tap for who they are Same subject: An agent writing an operating system may be relatively easy because of patterns memorized in training data, so it says little about agents' ability to create novel software. — tap to centre the map on it An agent writing an operating systemmay be relatively easy because ofpatterns memorized in training data,so it says little about agents'ability to create novel software. Last stated 6 months ago 22 May 2026 SK Sayash Kapoor — holds since 2026-05-22 — tap for who they are Same subject: Biological systems are basically collective intelligences. — tap to centre the map on it Biological systems are basicallycollective intelligences. Last stated 3 years ago 12 Mar 2024 ML Michael Levin — holds since 2024-03-12 — tap for who they are Same subject: The Abstraction and Reasoning Corpus can measure human-like general fluid intelligence and enable fair comparisons between AI systems and humans. — tap to centre the map on it The Abstraction and Reasoning Corpuscan measure human-like general fluidintelligence and enable faircomparisons between AI systems andhumans. Last stated 7 years ago 5 Nov 2019 FC François Chollet — holds since 2019-11-05 — tap for who they are Same subject: Combining an avocado and a chair into one image is evidence a model conceptually understands both, not that it memorised pictures of them. — tap to centre the map on it Combining an avocado and a chairinto one image is evidence a modelconceptually understands both, notthat it memorised pictures of them. Last stated 3 months ago 12 Aug 2026 CF Chelsea Finn — holds since 2026-08-12 — tap for who they are Same subject: Passing ARC-AGI does not amount to achieving AGI: o3 still fails on some very easy tasks, indicating fundamental differences from human intelligence. — tap to centre the map on it Passing ARC-AGI does not amount toachieving AGI: o3 still fails onsome very easy tasks, indicatingfundamental differences from humanintelligence. Last stated 2 years ago 20 Dec 2024 FC François Chollet — holds since 2024-12-20 — tap for who they are Same subject: One-shot or zero-shot settings are the fairest comparisons to human performance and important targets for future work. — tap to centre the map on it One-shot or zero-shot settings arethe fairest comparisons to humanperformance and important targetsfor future work. Last stated 6 years ago 28 May 2020 DA Dario Amodei — holds since 2020-05-28 — tap for who they are Same subject: Performance gains from scaling on exam-style benchmarks are orthogonal to intelligence, because those benchmarks can be hacked by memorizing in advance. — tap to centre the map on it Performance gains from scaling onexam-style benchmarks are orthogonalto intelligence, because thosebenchmarks can be hacked bymemorizing in advance. Last stated 2 years ago 6 Nov 2024 FC François Chollet — holds since 2024-11-06 — tap for who they are Same subject: Too many AI benchmarks are too sanitized: they only test well-defined problems. — tap to centre the map on it Too many AI benchmarks are toosanitized: they only testwell-defined problems. Last stated 4 weeks ago 27 Oct 2026 EC Edwin Chen — holds since 2026-10-27 — 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 Humans have a million times better sample efficiency than AI. Last stated 14 Nov 2026 · a week ago Holds Noah Smith Read this korrent →