Reasoning Is Not Model Improvement (manidoraisamy.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of manidoraisamy.com: Reasoning Is Not Model Improvement

First screen, captured 1 year ago.

Looks similar

Screenshot of manidoraisamy.com: The Era of Solopreneurs Is Here

The Era of Solopreneurs Is Here (manidoraisamy.com)

53 points by QueensGambit 1 year ago | 36 comments

Screenshot of answer.ai: Thoughts on a Month with Devin

Thoughts on a Month with Devin (answer.ai)

235 points by swyx 1 year ago | 130 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 answer.ai: Fine tune a 70B language model at home

Fine tune a 70B language model at home (answer.ai)

821 points by jph00 2 years ago | 197 comments

Answer.AI blog post announcing an open source system combining FSDP and QLoRA to train a 70B language model on two 24GB consumer GPUs.

qlora fsdp llm-fine-tuning answer-ai

Screenshot of answer.ai: Solveit – A course and platform for solving problems with code

Solveit – A course and platform for solving problems with code (answer.ai)

96 points by eries 1 year ago | 84 comments

Screenshot of Hacker News post: Show HN: System Prompt Learning – LLMs Learn Problem-Solving from Experience

Show HN: System Prompt Learning – LLMs Learn Problem-Solving from Experience

36 points by codelion 1 year ago | 11 comments