← 트렌딩

Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.

Formal-Verification-RSI

github.com

Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.

오픈소스

github.com 방문외부 사이트GitHub2,887 스타외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Formal Verification for Machine Learning Models Using Lean 4

    Framework for specifying and proving properties—such as robustness, fairness, and interpretability—of machine learning models using Lean 4.

    Hacker News52점GitHub스타 88github.com라이브러리오픈소스반응 2개최근 반응

  2. paperthin

    The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.

    GitHub스타 1,396github.com오픈소스최근 반응

  3. Akmon

    a Rust AI coding agent for regulated engineering

    Hacker News5점GitHub스타 36github.comCLI오픈소스반응 2개최근 반응

  4. Forall

    Spec-driven AI coding with formal verification

    Hacker News11점github.com오픈소스반응 3개최근 반응

  5. RSI-Anything

    JEPA world models for self-improving agents

    Hacker News8점GitHub스타 1,132github.com오픈소스반응 2개최근 반응