A dev's AGI eval: can it make $1M/year profit from one prompt per month?
JoshPurtell · x · 2026-11-02
Developer Josh Purtell argues the "Platonic eval" is a single threshold on a single task — his AGI test is whether a system, without being trained for it, can generate $1M/year in profit from just one prompt per month. He stresses that distinguishing evals from training data matters so we can teach AIs to improve both.
More from coding & agent
- Zed CEO shows off SLAG, a 1-8 player party platformer built with Codex — zeeg · 2026-11-02
- Grok Bot tip: have it write a Python script and run it on a routine to save usage — nima_owji · 2026-11-02
- mnemos v2 MCP nearly ready: watch your agent's memories form live in an in-app browser — RileyRalmuto · 2026-11-02
- Supabase launches Compute in private alpha: run agents next to Postgres — dshukertjr · 2026-11-02
- ChatGPT Sites packs login, built-in database, analytics and MCP hosting — gabrielchua · 2026-11-02
- Pain points of deploying AI agents: guardrails too tight slow automation, too loose invite risk — bibinprasannan · 2026-11-02