Self-improving code for any git repo: give it a measurable goal, a coding agent (Claude Code or Aider) proposes changes, the kernel scores them, keeps winners and rolls back failures. Open-source AlphaEvolve / FunSearch-style evolution loop, sandboxed, with an auditable ledger.
HarnessMM: recursive self-improvement for harness token efficiency
- agent-harness
- llm-agents
- recursive-self-improvement
- token-efficiency
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
TranslatedA guide to avoiding scams in the human world: 373 scam breakdowns covering 16 categories, including fake-order task scams (刷单), pig-butchering scams (杀猪盘), AI face-swapping, and scams targeting the elderly; includes real case reports, everyday self-check lists, PDF/EPUB/Anki downloads, and a scam-avoidance mini-game with 12 rounds
- anti-fraud
- anti-scam
- chinese
- scam-awareness