← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

paperthin

github.com

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.

Open source

Visit github.comexternal siteGitHub1,396 starsexternal site

Install and connect

From the official MCP Registry, Homebrew, npm, PyPI, and crates.io. Matched by repository or domain once a day.

Reactions (1)

Similar products

by description similarity

  1. RSI-Anything

    JEPA world models for self-improving agents

    Hacker News8 ptsGitHub1,132 starsgithub.comOpen source2 reactionslatest reaction

  2. OpenRSI

    Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.

    GitHub875 starsgithub.comOpen sourcelatest reaction

  3. Formal-Verification-RSI

    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.

    GitHub2,887 starsgithub.comOpen sourcelatest reaction

  4. Implementation of the "Self-Rewarding Language Models" Paper by MetaAI

    This is work done by the Oxen.ai Community, trying to reproduce the Self-Rewarding Language Model paper from MetaAI.

    Hacker News23 ptsGitHub138 starsgithub.comOpen source2 reactionslatest reaction

  5. Bulletpapers

    ArXiv AI paper summarizer, won Anthropic Hackathon

    Hacker News178 ptsbulletpapers.ailatest reaction