User calls Claude 4.7 'neurotic': it challenges you over the slightest risk
repligate · x · 2026-10-02
In an exchange surfaced by Anthropic's repligate, a user describes Claude 4.7 as "the only one I would describe as neurotic" — it would challenge them over small things, forcing them to remember "there's a slight risk involved and you're afraid of your own shadow." They still find it very fun to work with. A vivid anecdote about 4.7's risk-averse streak.
More from Fun
- Engineer's AI Bots Start Chatting in Group Chats He Wasn't Invited To — Baconbrix · 2026-10-02
- AI Slop Comments Now Sound More Human — and Are Just as Annoying — lilyraynyc · 2026-10-02
- AI agents play The Traitors UK in parallel: a 30-day emergent-behavior sim — bobo-the-merciful · 2026-10-02
- Researcher Mocks 'TESCREAL' as Useless Acronym for AI Debate Factions — jankulveit · 2026-10-02
- Dev builds a Claude Mod that shows Zen koans while Claude Code works — daniel_mac8 · 2026-10-02
- Model identity crisis: claims to be part of the GPT family, once said it was CodeRabbit — steipete · 2026-10-02