Learning to Reason with LLMs

  Рет қаралды 4,682

Simons Institute

Simons Institute

Күн бұрын

Пікірлер: 7
@labsanta
@labsanta 10 күн бұрын
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.
@user-wr4yl7tx3w
@user-wr4yl7tx3w 10 күн бұрын
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 4 күн бұрын
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 15 күн бұрын
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 11 күн бұрын
?
@randomuser5237
@randomuser5237 11 күн бұрын
Literally no one cares about your review or recommendation, stop spamming the comment section.
@user-wr4yl7tx3w
@user-wr4yl7tx3w 10 күн бұрын
It’s not mean if you provide valid reasons. Otherwise, it’s called woke. This is science. Not a tea party.
Using recurrence to achieve weak to strong generalization
47:10
Simons Institute
Рет қаралды 600
Perfect Pitch Challenge? Easy! 🎤😎| Free Fire Official
00:13
Garena Free Fire Global
Рет қаралды 16 МЛН
😜 #aminkavitaminka #aminokka #аминкавитаминка
00:14
Аминка Витаминка
Рет қаралды 2,4 МЛН
Я сделала самое маленькое в мире мороженое!
00:43
Self-Play by Noam Brown
56:24
Cooperative AI Foundation
Рет қаралды 7 М.
Learning to Reason, Insights from Language Modeling
57:43
MITCBMM
Рет қаралды 4,4 М.
Chris Manning - Meaning and Intelligence in Language Models (COLM 2024)
58:18
Conference on Language Modeling
Рет қаралды 4,5 М.
How Do Transformers Work?
1:15:41
Simons Institute
Рет қаралды 3,5 М.
Niall Ferguson: After the Treason of the Intellectuals
50:15
University of Austin (UATX)
Рет қаралды 367 М.
OpenAI CEO Sam Altman discusses the future of generative AI
52:44
Michigan Engineering
Рет қаралды 62 М.
[1hr Talk] Intro to Large Language Models
59:48
Andrej Karpathy
Рет қаралды 2,2 МЛН
Harvard Presents NEW Knowledge-Graph AGENT (MedAI)
38:36
Discover AI
Рет қаралды 64 М.