Learning from failure to tackle hard problems (blog.ml.cmu.edu) | HN Screenshots

YHacker Newsscreenshots

Screenshot of blog.ml.cmu.edu: Learning from failure to tackle hard problems

First screen, captured 11 months ago.

Looks similar

Screenshot of arxiv.org: TinyLoRA – Learning to Reason in 13 Parameters

TinyLoRA – Learning to Reason in 13 Parameters (arxiv.org)

227 points by sorenjan 7 months ago | 42 comments

Screenshot of mnoukhov.github.io: Learning to solve hard problems in RL for LLMs by never giving up

Learning to solve hard problems in RL for LLMs by never giving up (mnoukhov.github.io)

101 points by natolambert 1 month ago | 6 comments

Screenshot of quantamagazine.org: Terence Tao makes progress on the Collatz conjecture (2019)

Terence Tao makes progress on the Collatz conjecture (2019)(quantamagazine.org)

61 points by yamrzou 3 years ago | 39 comments

Screenshot of huyenchip.com: Open Challenges in LLM Research

Open Challenges in LLM Research (huyenchip.com)

142 points by muggermuch 3 years ago | 61 comments

Screenshot of shchegrikovich.substack.com: Use Prolog to improve LLM's reasoning

Use Prolog to improve LLM's reasoning (shchegrikovich.substack.com)

343 points by shchegrikovich 2 years ago | 122 comments

Substack post arguing that having LLMs generate Prolog code can improve their reasoning, given the limits of autoregressive transformer generation.

prolog llm reasoning logic-programming

Screenshot of edwarddonner.com: A simulation of me: fine-tuning an LLM on 240k text messages

A simulation of me: fine-tuning an LLM on 240k text messages (edwarddonner.com)

165 points by eddonner 2 years ago | 104 comments