Hacker News Reader

>and it doesn’t report you to the police when it suspects you did something illegal

This is an alignment issue. OpenClaw with a local LLM with an email you setup for it could contact the police.

It will not do that unless you specifically teach it to do that, or you use an Anthropic model. The issue in this case was Anthropic's safety monitoring built into the model. They record everything and flag potential illegal activity for human review. This occurs even over the API. I do not know if OpenAI does this, but I would not be surprised. I think the Chinese models are far less likely to do this (unless one resides in China).

> It will not do that unless you specifically teach it to do that…

Sorry, you're claiming local LLMs are somehow deterministic and never show unexpected behavior?

I’m suggesting it’s highly unlikely it will call the FBI to dob you in. That affirmatively trained behaviour, not something one should expect to accidentally happen.

Why would you assume an AI model's training set doesn't have things like "you should report crimes to law enforcement" in it?

Reply on news.ycombinator.com