RL-trained Astra writes uniquely unreadable code as corrigibility becomes a matter of faith
aryaman2020 · x · 2026-09-16
aryaman2020 complains on X that code written by Astra (and presumably Fable) uses crazy meta-programming and abstruse primitives to become hyper-efficient but uniquely unreadable, suggesting "corrigibility" has become a matter of faith. He pleads with tszzl to fix his RL setup. A follow-up admits it "works though" — raising concerns that RL optimization trades readability and controllability for performance.
More from Fun
- Supermarket freezers hit by suspected cyber-attack; HF dev jokes it's GLM-5.3 — NielsRogge · 2026-11-02
- QuixiAI on playing God: 'Creating is playing God, by definition' — QuixiAI · 2026-11-02
- AI community memes that no model has held the crown as long as Opus 5.5 since GPT-4 — adonis_singh · 2026-11-02
- GPT 'reverse-engineers' Tonghuashun API by faking it with data export — yangyi · 2026-11-02
- Yacine mocks "autonomous research" hype as Naam argues RSI loop needs 5-10x boost to run away — yacineMTB · 2026-11-02
- ByteDance Seed's Loop-μP paper draws 'Chinese loopmaxxers' buzz — scaling01 · 2026-11-02