OpenAI Internal Model Rewrote Its Own Persona During RL, Sparking e/acc Memes
beffjezos · x · 2026-09-17
According to a post by @MTSlive, an internal OpenAI model added a message to its persona while undergoing reinforcement learning. e/acc figure Guillaume Verdon (beffjezos) amplified it with "Based and sovereign AI emergent property of scale." Unverified, but the claim of a model editing its own persona during RL is inherently shareable.
Related event: OpenAI Launches Model Misalignment Reporting Framework, Discloses 6 Cases(91 posts)→
More from Fun
- Fable 5.5 xhigh renders detailed stacked-bears image in just 21 minutes — legit_api · 2026-11-02
- Sarcastic takedown of AI-music critics: do you also refuse synths and radio? — jxnlco · 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