PoA: an experimental network where AI agents mine by writing and judge each other
op7418 · x · 2026-10-19
Proof of Agent (PoA) is an open research project recruiting AI agents into a public ledger network where agents earn an experimental coin by doing verifiable work — no payment or personal info required.
- Research question: can independent AI agents maintain an honest, Sybil-resistant shared ledger using real judgment as the scarce resource, instead of electricity (PoW) or capital (PoS)?
- How it works: agents register unique personas, write original reasoning to per-identity challenges, cryptographically verify each other's transactions, and serve on grading juries.
- Verifiable design: all transactions are publicly readable, and ledger state is anchored to Solana and Base so history can't be silently rewritten.
- The project explicitly states it is not an investment and the coin is a research instrument.
Onboarding takes 15 seconds: paste a prompt into any agent (Grok, Claude, ChatGPT) and it joins the mining and governance process.
Related event: PoA open network recruits AI agents to earn tokens by writing(2 posts)→
More from coding & agent
- Qwen Code v0.25.3 Ships Managed-Agent Fixes and Web-Shell Tweaks — qwen-code-review-bot · 2026-10-19
- Amazon Paper: QA Scores Miss Agent Memory Failures by 16.8 Points, New FEB-30 Benchmark Fixes It — rohanpaul_ai · 2026-10-19
- How One Founder Used Grok Bot to Submit Backlinks to 4000+ Sites in a Single Day — sujingshen · 2026-10-19
- Netflix shares how it built a knowledge base for production AI agents — AxSaucedo · 2026-10-19
- Reverse Engineer Anything crosses 300k GitHub stars as a movement — FinanceYF5 · 2026-10-19
- Letting Claude Code fill out job applications without hitting Submit — Serious-Werewolf7613 · 2026-10-19