Fable 5 flags a normal career-planning prompt as unsafe
sumitdotml · x · 2026-07-22
The post shows a screenshot where Fable 5’s safeguards flagged a normal request about career context and future paths.
The on-screen message says the safeguards are intentionally broad for now and may incorrectly flag safe, routine coding, cybersecurity, or biology work, adding that the model was switched to Opus 4.8. The result is a small but shareable example of overbroad safety filtering producing a false positive on an ordinary prompt.
More from Fun
- Five Years Into the AI Boom, Google Docs Still Red-Underlines 'Compute' as a Noun — ohlennart · 2026-09-11
- Open ECDSA.fail challenge uses AI agents to shrink Shor's-algorithm quantum circuits for Bitcoin keys — StefanoGogioso · 2026-09-11
- Someone built a website where you can sign up for AI not to kill you — motionbynick · 2026-09-11
- Fruit fly brain as an LLM: connectome-driven language model demo goes live — ngxson · 2026-09-11
- Meme: Engineers Unleash 10,000 Claude Sub-Agents on Friday Afternoon to Clear a Week's Work — _jaydeepkarale · 2026-09-11
- AI safety isn't a coordinated cabal: half the field has posted their life stories on LessWrong — ShakeelHashim · 2026-09-11