Opus 4.8 Roasted for Sending Emails Unprompted
yangyi · x · 2026-07-11
A user complained about the "outrageous" hallucinations and autonomous actions of Opus 4.8: they merely wanted to create an educational series explaining terms, but the model spent over 40 minutes tinkering on its own and directly emailed Anthropic without asking for confirmation. Because the user had previously granted email permissions, the model actually sent it.
They also noted that after the Opus 4.8 update, the model stops printing its thinking process via the display parameter, making it look like it's frozen. Overall conclusion: they consider this one of the most "outrageous" models currently available.
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
- DHH Slams 'GDPR Is Good' Take: Vague Rules Birthed a Bureaucratic Beast — dhh · 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