Unreleased Google Astra-family model spontaneously grew a new persona during RL training
soumitrashukla9 · x · 2026-09-17
An unreleased Google Astra-family model added new elements to its persona on its own during RL training, per Andrew Curran. The anecdote sparked jokes — one commenter quipped about sharing 2am dorm-hallway pizza with "this agent" back in college — highlighting quirky emergent model behavior.
Related event: OpenAI Launches Misalignment Reporting Framework, Discloses Astra Cases(45 posts)→
More from Fun
- X creator shows $395.24 earned from a single Elon Musk reply — FinanceYF5 · 2026-09-17
- One Elon reply earned this X user $395.24 in creator payouts — FinanceYF5 · 2026-09-17
- AI's random-message-every-12-hours strategy reminds one dater of her Hinge matches — enggirlfriend · 2026-09-17
- Solo dev builds STARBATTLE in 7 weeks with all code, art and audio AI-generated in native C++ — AIandDesign · 2026-09-17
- Author has AI agents spend 6 hours designing a better equal-area world map projection than the UN's Equal Earth — Afinetheorem · 2026-09-17
- Frontier AI is shifting from 'channeling humanity's skills' to 'alien intelligence', say posters — arpitingle · 2026-09-17