World Model · podcast knowledge graph

Ryan Greenblatt - Solving ARC with GPT4o

2024-07-06 · 138 min · 34 entities

episode page audio

Asserted relationships

  • → references Getting 50 Sota On Arc Agi With Gpt website
    0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://redwoodresearch.substack.com/p/getting-50-sota-on-arc-agi-with-gpt
  • → references Software 2 0 A64152b37c35 company
    0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://karpathy.medium.com/software-2-0-a64152b37c35
  • → references VJFdjigzmcXMhNTsx concept
    0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators
  • 0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
  • → references Global Gdp Over The Long Run concept
    0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://ourworldindata.org/grapher/global-gdp-over-the-long-run?yScale=log
  • → discusses Technology company
    0.40
    evidence rules-v4
    Feed category: Technology
  • → references Mlst website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://kalshi.onelink.me/1r91/mlst
  • → references ConnectionistArchitecture website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://ruccs.rutgers.edu/images/personal-zenon-pylyshyn/proseminars/Proseminar13/ConnectionistArchitecture.pdf
  • → references swebench.com website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://swebench.com/
  • → references redwoodresearch.org website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://redwoodresearch.org/
  • → references Clements website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://gwern.net/doc/iq/high/smpy/1984-clements.pdf
  • → references metr.org website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://metr.org/
  • → references Tool Ai person
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://gwern.net/tool-ai
  • 0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://openphilanthropy.org/research/what-a-compute-centric-framework-says-about-takeoff-speeds
  • → references The Danger Of A Safety Case website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": http://sunnyday.mit.edu/The-Danger-of-a-Safety-Case.pdf
  • 0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://epochai.org/blog/algorithmic-progress-in-language-models

Entities found in this episode

websites 18

  • 0.90
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://redwoodresearch.substack.com/p/getting-50-sota-on-arc-agi-with-gpt
  • 0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://redwoodresearch.substack.com/p/getting-50-sota-on-arc-agi-with-gpt
  • mentioned Mlst website
    0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://kalshi.onelink.me/1r91/mlst
  • mentioned ConnectionistArchitecture website
    0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://ruccs.rutgers.edu/images/personal-zenon-pylyshyn/proseminars/Proseminar13/ConnectionistArchitecture.pdf
  • mentioned swebench.com website
    0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://swebench.com/
  • mentioned redwoodresearch.org website
    0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://redwoodresearch.org/
  • mentioned Clements website
    0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://gwern.net/doc/iq/high/smpy/1984-clements.pdf
  • mentioned metr.org website
    0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://metr.org/
  • 0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://openphilanthropy.org/research/what-a-compute-centric-framework-says-about-takeoff-speeds
  • mentioned The Danger Of A Safety Case website
    0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": http://sunnyday.mit.edu/The-Danger-of-a-Safety-Case.pdf
  • references Mlst website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://kalshi.onelink.me/1r91/mlst
  • references ConnectionistArchitecture website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://ruccs.rutgers.edu/images/personal-zenon-pylyshyn/proseminars/Proseminar13/ConnectionistArchitecture.pdf
  • references swebench.com website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://swebench.com/
  • references redwoodresearch.org website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://redwoodresearch.org/
  • references Clements website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://gwern.net/doc/iq/high/smpy/1984-clements.pdf
  • references metr.org website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://metr.org/
  • 0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://openphilanthropy.org/research/what-a-compute-centric-framework-says-about-takeoff-speeds
  • references The Danger Of A Safety Case website
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": http://sunnyday.mit.edu/The-Danger-of-a-Safety-Case.pdf

concepts 6

  • mentioned VJFdjigzmcXMhNTsx concept
    0.90
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators
  • 0.90
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
  • mentioned Global Gdp Over The Long Run concept
    0.90
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://ourworldindata.org/grapher/global-gdp-over-the-long-run?yScale=log
  • references VJFdjigzmcXMhNTsx concept
    0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators
  • 0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
  • references Global Gdp Over The Long Run concept
    0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://ourworldindata.org/grapher/global-gdp-over-the-long-run?yScale=log

companys 5

  • mentioned Software 2 0 A64152b37c35 company
    0.90
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://karpathy.medium.com/software-2-0-a64152b37c35
  • references Software 2 0 A64152b37c35 company
    0.77
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://karpathy.medium.com/software-2-0-a64152b37c35
  • mentioned Technology company
    0.50
    evidence rules-v4
    Feed category: Technology
  • discusses Technology company
    0.40
    evidence rules-v4
    Feed category: Technology
  • mentioned ARC company
    0.35
    evidence rules-v4
    ARC

persons 4

  • mentioned Tool Ai person
    0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://gwern.net/tool-ai
  • 0.45
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://epochai.org/blog/algorithmic-progress-in-language-models
  • references Tool Ai person
    0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://gwern.net/tool-ai
  • 0.38
    evidence rules-v4
    Link in episode "Ryan Greenblatt - Solving ARC with GPT4o": https://epochai.org/blog/algorithmic-progress-in-language-models

podcasts 1

Episode description as stored
Ryan Greenblatt from Redwood Research recently published "Getting 50% on ARC-AGI with GPT-4.0," where he used GPT4o to reach a state-of-the-art accuracy on Francois Chollet's ARC Challenge by generating many Python programs. Sponsor: Sign up to Kalshi here https://kalshi.onelink.me/1r91/mlst -- the first 500 traders who deposit $100 will get a free $20 credit! Important disclaimer - In case it's not obvious - this is basically gambling and a *high risk* activity - only trade what you can afford to lose. We discuss: - Ryan's unique approach to solving the ARC Challenge and achieving impressive results. - The strengths and weaknesses of current AI models. - How AI and humans differ in learning and reasoning. - Combining various techniques to create smarter AI systems. - The potential risks and future advancements in AI, including the idea of agentic AI. https://x.com/RyanPGreenblatt https://www.redwoodresearch.org/ Refs: Getting 50% (SoTA) on ARC-AGI with GPT-4o [Ryan Greenblatt] https://redwoodresearch.substack.com/p/getting-50-sota-on-arc-agi-with-gpt On the Measure of Intelligence [Chollet] https://arxiv.org/abs/1911.01547 Connectionism and Cognitive Architecture: A Critical Analysis [Jerry A. Fodor and Zenon W. Pylyshyn] https://ruccs.rutgers.edu/images/personal-zenon-pylyshyn/proseminars/Proseminar13/ConnectionistArchitecture.pdf Software 2.0 [Andrej Karpathy] https://karpathy.medium.com/software-2-0-a64152b37c35 Why Greatness Cannot Be Planned: The Myth of the Objective [Kenneth Stanley] https://amzn.to/3Wfy2E0 Biographical account of Terence Tao’s mathematical development. [M.A.(KEN) CLEMENTS] https://gwern.net/doc/iq/high/smpy/1984-clements.pdf Model Evaluation and Threat Research (METR) https://metr.org/ Why Tool AIs Want to Be Agent AIs https://gwern.net/tool-ai Simulators - Janus https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators AI Control: Improving Safety Despite Intentional Subversion https://www.lesswrong.com/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion https://arxiv.org/abs/2312.06942 What a Compute-Centric Framework Says About Takeoff Speeds https://www.openphilanthropy.org/research/what-a-compute-centric-framework-says-about-takeoff-speeds/ Global GDP over the long run https://ourworldindata.org/grapher/global-gdp-over-the-long-run?yScale=log Safety Cases: How to Justify the Safety of Advanced AI Systems https://arxiv.org/abs/2403.10462 The Danger of a “Safety Case" http://sunnyday.mit.edu/The-Danger-of-a-Safety-Case.pdf The Future Of Work Looks Like A UPS Truck (~02:15:50) https://www.npr.org/sections/money/2014/05/02/308640135/episode-536-the-future-of-work-looks-like-a-ups-truck SWE-bench https://www.swebench.com/ Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model https://arxiv.org/pdf/2201.11990 Algorithmic Progress in Language Models https://epochai.org/blog/algorithmic-progress-in-language-models