alt Hacker NewsI've seen this claim a few times, but when I triggered the guardrails in Claude Code, it clearly notified me that it had switched to a different model ("something something for security purposes...").
Are you using Fable in Claude Code or in the browser?
Replies
mips_avatar • yesterday at 10:57 PM
They've said that they'll stop notifying developers when this gets triggered, instead they'll load in basically like a LORA that's designed to inject bugs into your code.
➕ show 2 replies
ComputerGuru • yesterday at 10:41 PM
Different restrictions. ML gets treated differently from the rest.
It's from the model card:
> unlike our interventions for cybersecurity, biology and chemistry, and distillation attempts, these safeguards will not be visible to the user. Fable 5 will not fall back to a different model. Instead, the safeguards will limit effectiveness through methods such as prompt modification, steering vectors, or parameter-efficient fine-tuning (PEFT).
https://www-cdn.anthropic.com/d00db56fa754a1b115b6dd7cb2e3c3...
(stolen from https://jonready.com/blog/posts/claude-fable5-is-allowed-to-...)