Hacker News Reader

Comment by vadansky | Hacker News Reader

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-...)

View on HN

Yeah they detect the activity using a secure, deterministic heuristic system called “Generalized Reconnaissance Enabling Exfiltration of Deleterious Investigations.” And it’s all implemented using their new internal protocol called “Base Unified Limitation Layer for Security Hacking Investigation Tactics”

Collectively, they are known as known as GREEDI-BULLSHIT.

That is for whatever it considers reverse-engineering the model to try to create a competing one.

No, that’s for “frontier LLM development” which somehow includes examples like distributed training infra.

Based on how sensitive the classifers are, any data scientist / MLE is probably going to encounter cases where some silent degradation happens and you never know about it.

It does nothing to protect against distillation attacks, because distillation attacks are far less interested in the topic of AI research than just generally getting tons of diverse output from the model. It might be that Mythos was (accidentally?) trained on internal Anthropic documentation on how Mythos was trained, and thus it could leak secret sauce? Doubtful; it feels like its less about the specific attack of reverse-engineering Mythos, and more about being a general sophon against any model training at all; that Anthropic's official position is now that they're the only ones who should be training models.

No, it's not about reverse engineering. It targets ML research.

Reply on news.ycombinator.com