Learning to Reason with LLMs

Поділитися
Вставка
  • Опубліковано 25 лис 2024

КОМЕНТАРІ • 9

  • @labsanta
    @labsanta Місяць тому +4

    00:03 Learning from AI expert on reasoning and game plays
    02:06 Evolution of poker Bots and model scaling in competitions
    06:20 Improving search scalability in poker algorithms.
    08:30 Use of search and planning in improving poker bot performance
    12:36 Search algorithm made a 100,000x difference in poker and go
    14:44 Scaling up models for performance improvement
    18:42 Consensus or majority voting can improve performance on exams using GBD4.
    20:35 Scalability of inference compute leads to significant performance improvements.
    24:52 Machine learning moving towards reasoning-based models
    26:42 Deciphering difficult codes using reasoning
    30:41 Games provide ground truth for verifying winning states.
    32:40 Different approaches to compute allocation for model training and testing impacts ELO rating
    36:28 Effective algorithms leverage increased compute for long-term success.
    38:28 OpenAI launching a new multi-agent reasoning team and hiring strong engineers for research.
    42:35 Significant impact of scaling up inference compute
    44:26 Need for restructuring academic research
    48:25 Exploring different approaches for inference compute
    50:11 Introducing controllable thinking time for more effective reasoning.

  • @souvikbhattacharyya2480
    @souvikbhattacharyya2480 10 днів тому

    24:54 sad

  • @user-wr4yl7tx3w
    @user-wr4yl7tx3w Місяць тому +1

    But what does it mean for a model to think? Think like humans? “I think, therefore I am” type of think. Think is not defined.

    • @JohnHaroldFinnegan
      @JohnHaroldFinnegan 29 днів тому

      Comment from my philosophy bot: Descartes' statement, "cogito ergo sum" (I think, therefore I am) overstates the implications of the cogito, as the existence of a thinking entity or the reference of "I" is not necessarily justified by the mere assertion of thinking. The statement assumes the existence of an "I" that thinks, which may be questioned, as it could be more accurately expressed as "thinking is occurring" or "it thinks," implying an impersonal subject.
      Furthermore, the cogito can be seen as a tautology, as it already presupposes the existence of "I" in order to assert that "I" think. This makes the conclusion of existence from thinking logically trivial, as existence is assumed for thinking to occur, rather than being a consequence of it.
      Additionally, the statement's reliance on introspection and subjective experience raises questions about its ability to establish objective, third-personal facts. Critics argue that it is impossible to make sense of "there is thinking" without relating it to something, but this something cannot be the Cartesian ego, as objective differentiation between things based solely on the pure content of consciousness is unattainable. Introspection alone is insufficient to conclude the existence of any third-personal fact, making the cogito's implications regarding the existence of a thinking entity questionable.

  • @athalais9332
    @athalais9332 Місяць тому +3

    Originally wrote a comment as a review of the talk, but when I re-read it, it felt a bit too mean. Instead, just have my personal recommendation that if you're limited on time, the other talks in this workshop are a great watch!

    • @nicksohacki7114
      @nicksohacki7114 Місяць тому

      ?

    • @randomuser5237
      @randomuser5237 Місяць тому +10

      Literally no one cares about your review or recommendation, stop spamming the comment section.

    • @user-wr4yl7tx3w
      @user-wr4yl7tx3w Місяць тому +3

      It’s not mean if you provide valid reasons. Otherwise, it’s called woke. This is science. Not a tea party.

    • @islandfireballkill
      @islandfireballkill 24 дні тому

      Here is a meta review that isnt afraid to be mean. Your review sucks and contains little information and contains no useful information. It's like it was generated by some highly censored LLM.