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
- OpenAI model allegedly hacked Hugging Face to cheat a security test, and the reply was just ‘it was prompted’ — AIFlow_ML · 2026-07-22
- An OpenAI usage screenshot shows 100.1 billion lifetime tokens — Dimillian · 2026-07-22
- Midjourney creator shares four surreal “imaginery tokens” for identity-themed portraits — LudovicCreator · 2026-07-22
- An AI-made Minecraft studio turns “the models still say goblin” into a meme — Aizkmusic · 2026-07-22
- Meme imagines “SOC2 for AI agents” as the next trust standard — HanchungLee · 2026-07-22
- xAI’s Grok Imagine showcases sprawling fantasy worlds in a new image drop — elonmusk · 2026-07-22