Intro Video를 살펴보십시오.

Codex를 원하십니까? 신선한 코덱 스레드로 붙여 넣기:

기술이 스스로 개선할 수 있다면?

Recursive self-improvement는 루프에없는 더 나은 시스템을 설명 할 때 AI 연구원의 구문입니다. 일반적으로 생각 실험입니다. 이것은 당신의 노트북에 실행.

Skill RSI 목표를 부여하고 에이전트 스킬을 쫓아냅니다. 당신이 이미 가지고있는 기술을 손으로하고 대신 더 나은 것을 만듭니다. 그런 다음 반복 시작 : 기술을 연구하고, 도움이되는 것에 대한 이론을 형성, 변형을 구축, 그것을 테스트, 우승자를 유지. 다시, 그 자신에, 당신이 그것을 중지 때까지.

단일 라인을 작성하기 전에 도메인을 연구합니다. 그것은 sourced 주장으로 필드를 연구, 실무자 구급차, 그리고 간텍스 상황에, 다음 투과로 컴파일: 기술 봉사하는 사람의 작업 모델, 우수한 출력 같은 것, 캐치의 실패 모드, 전문가의 구별 초보자 평평한, 그리고 강한 의견은 "좋은"이 의미하는 권위. 그 투과는 공유된지도가 나중에 루프가 켜져 있으며, 드리프팅에서 작업을 유지하고 있습니다.

Skill RSI

Watch the Intro Video here

Want Codex to install it for you? Paste this into a fresh Codex thread:

Set up Skill RSI from https://github.com/justinwetch/Skill-RSI. Clone the repo, read AGENTS.md, install dependencies, build the UI, configure and install the Codex plugin, run the plugin smoke checks, and tell me when to start a fresh Codex thread. Do not start any model-backed Skill RSI run yet.

What if a skill could improve itself?

Recursive self-improvement is the phrase AI researchers reach for when they describe systems that get better without us in the loop. Usually it’s a thought experiment. This one runs on your laptop.

Give Skill RSI a goal and it writes an Agent Skill to chase it. Hand it a skill you already have and it makes that one better instead. Then the loop starts: study the skill, form a theory about what would help, build a variant, test it, keep the winner. Again and again, on its own, until you stop it.

Before it writes a single line, it studies the domain. It researches the field into sourced claims, practitioner vocabulary, and intertextual context, then compiles them into an ontology: a working model of who the skill serves, what excellent output looks like, the failure modes worth catching, the expert distinctions novices flatten, and the authorities whose strong opinions sharpen what “good” means here. That ontology becomes the shared map every later loop builds on and the guardrail that keeps the work from drifting.

Once there’s a champion to beat, Skill RSI deconstructs it into more than a dozen testable surfaces, every one carrying a hypothesis, a regression risk, and a way to measure whether the change actually worked. Each loop the current champion is the control and the next variant is the treatment, both run against the same prompts under the same criteria. One variable moves at a time, so when a challenger wins, you know exactly what won.

Skill RSI improves skills the way a research lab works: every loop is an experiment whose results are kept and built on, including a record of dead ends, so it never wastes time re-testing what doesn’t work. Each pass starts better informed than the last, converging on what does.

You set the goal. The research, the experiments, the evaluation, and the record-keeping run themselves.

This is the sequel to SkillEval. SkillEval could tell you which of two skills was better. The question it left open was what to build next, and that part was still on you. Skill RSI closes the loop.

For the origin story, see Open Sourcing SkillEval.