korrents

On the map

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

← Video generation requires more world knowledge than image generation…

17 connected korrents · 14 moments from 12 Apr 2024 to 26 Oct 2026.

Everything filed under world models world models Everything filed under computer vision computer vision Everything filed under recursive self-improvement recursive self-improvement Everything filed under reinforcement learning reinforcement learning Everything filed under scaling laws scaling laws Everything filed under optimism optimism Everything filed under video games video games Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Video generation requires more world knowledge than image generation because of the need for temporal consistency across frames. Video generation requires more worldknowledge than image generation because ofthe need for temporal consistency acrossframes. Last stated 3 years ago 12 Apr 2024 LW Lilian Weng — holds since 2024-04-12 — tap for who they are Same subject: The industry is too optimistic about AI for video, and the consistency problem will not simply be remedied. — tap to centre the map on it The industry is too optimistic aboutAI for video, and the consistencyproblem will not simply be remedied. Last stated 2 years ago 30 Apr 2025 TS Tim Sweeney — holds since 2025-04-30 — tap for who they are Same subject: Video generation was not an algorithmic revolution: it was the same neural-network era with video added to the training data. — tap to centre the map on it Video generation was not analgorithmic revolution: it was thesame neural-network era with videoadded to the training data. Last stated 3 months ago 10 Aug 2026 FL Fei-Fei Li — holds since 2026-08-10 — tap for who they are Same subject: Real-time AI video generation can be used to create games and worlds generated on demand instead of pre-built. — tap to centre the map on it Real-time AI video generation can beused to create games and worldsgenerated on demand instead ofpre-built. Last stated 2 months ago 4 Sept 2026 KK Kevin Kelly — holds since 2026-09-04 — tap for who they are Same subject: Video never became intelligence the way text did because text arrives already abstracted into the bits humans care about. — tap to centre the map on it Video never became intelligence theway text did because text arrivesalready abstracted into the bitshumans care about. Last stated a year ago 12 Sept 2025 SL Sergey Levine — holds since 2025-09-12 — tap for who they are Same subject: A model that can predict the next frames of a video coherently understands the world, in the only sense of the word that is doing any work. — tap to centre the map on it A model that can predict the nextframes of a video coherentlyunderstands the world, in the onlysense of the word that is doing anywork. Last stated a year ago 23 Jul 2025 DH Demis Hassabis — holds since 2025-07-23 — tap for who they are Same subject: The companies that already control the largest troves of real-world video data will be first to build successful world models. — tap to centre the map on it The companies that already controlthe largest troves of real-worldvideo data will be first to buildsuccessful world models. Last stated 3 months ago 10 Aug 2026 KK Kevin Kelly — holds since 2026-08-10 — tap for who they are Same subject: High-quality video data, especially paired with text, is harder to collect at scale than image or text data. — tap to centre the map on it High-quality video data, especiallypaired with text, is harder tocollect at scale than image or textdata. Last stated 3 years ago 12 Apr 2024 LW Lilian Weng — holds since 2024-04-12 — tap for who they are Same subject: Having a job to do is what makes perception tractable, which is why an embodied model can learn from vision where a video model cannot. — tap to centre the map on it Having a job to do is what makesperception tractable, which is whyan embodied model can learn fromvision where a video model cannot. Last stated a year ago 12 Sept 2025 SL Sergey Levine — holds since 2025-09-12 — tap for who they are Same subject: A ban on self-recursive improvement in AI models would create a big incentive for some other parts of the world to invest a lot more in compute. — tap to centre the map on it A ban on self-recursive improvementin AI models would create a bigincentive for some other parts ofthe world to invest a lot more incompute. Last stated a month ago 22 Sept 2026 TC Tyler Cowen — holds since 2026-09-22 — tap for who they are Same subject: A sealed machine that redesigns itself will eventually redesign everything that touches its seal. — tap to centre the map on it A sealed machine that redesignsitself will eventually redesigneverything that touches its seal. Last stated 2 weeks ago 21 Oct 2026 BM Bruno Maçães — holds since 2026-10-21 — tap for who they are Same subject: AI is already inside the recursive self-improvement loop — what the labs have shipped in recent weeks shows the cycle has started. — tap to centre the map on it AI is already inside the recursiveself-improvement loop — what thelabs have shipped in recent weeksshows the cycle has started. Last stated 3 months ago 3 Aug 2026 CP Chamath Palihapitiya — holds since 2026-08-03 — 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 2 months ago 26 Aug 2026 HK Henrik Karlsson — holds since 2026-08-26 — 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 3 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 12 months ago 17 Nov 2025 AK Andrej Karpathy — holds since 2025-11-17 — tap for who they are Same subject: "Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next. — tap to centre the map on it "Scaling" was powerful because itwas one word: naming a researchdirection is what tells a wholefield what to do next. Last stated 11 months ago 25 Nov 2025 IS Ilya Sutskever — holds since 2025-11-25 — tap for who they are Same subject: A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. — tap to centre the map on it A benchmark result should bereported under a stated budget, oras a curve against test-time compute— never as a single number. Last stated 4 months ago 26 Jun 2026 NB Noam Brown — holds since 2026-06-26 — tap for who they are Same subject: A CPU and memory crunch is coming. — tap to centre the map on it A CPU and memory crunch is coming. Last stated 2 weeks ago 26 Oct 2026 DM Dillon Mulroy — holds since 2026-10-26 — 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 Video generation requires more world knowledge than image generation because of the need for temporal consistency across frames. Last stated 12 Apr 2024 · 3 years ago Holds Lilian Weng Read this korrent →