← 최신 프로덕트

AutoThink

Boosts local LLM performance with adaptive reasoning. I built AutoThink, a technique that makes local LLMs reason more efficiently by adaptively allocating computational resources based on query complexity.

news.ycombinator.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. ThinkGPT

    github.com

    a library to prompt GPT to think, memorize and self-refine

    Hacker News48점

  2. Speeding up LLM inference 2x times (possibly)

    asciinema.org

    Here's a project I've been working on for the last few months.

    Hacker News419점

  3. KillSwitch

    killswitch-lang.org

    a programming language designed to be difficult for LLMs

    Hacker News10점

  4. Crespo

    github.com

    Tree-sitter AST blueprints instead of raw code for LLMs

    Hacker News14점

  5. Undermind

    undermind.ai

    Deep scientific paper search with adaptive LLMs

    Hacker News49점