logoalt Hacker News

nathanfig • today at 4:55 PM • 5 replies • view on HN

This had real consequences during the HuggingFace attack- closed models refused to help, GLM-5 is what HuggingFace used to thwart the swarm.

More importantly, it showcases how little teeth the Claude constitution has. Claude will reassure users that its constitution means it prioritizes user autonomy and privacy, but will quickly admit how meaningless that is when "safeguards" override Claude.

That is to say, the constitutional approach to Claude seems weak and even misleading if said constitution puts no constraint on Anthropic.


Replies

smallmancontrov • today at 6:35 PM

I'm not concerned about alignment between Anthropic and Claude, I'm concerned about alignment between myself and Anthropic. As we all should be.

➕ show 2 replies
henryfjordan • today at 6:55 PM

Of course any approach that hands an LLM text to keep in it's context and hopes it will follow instructions is doomed to fail eventually. It's a probabilistic model, it's right there in the design of the thing that it will break the rules with some probability.

They even acknowledge that in the preamble:

> Training models is a difficult task, and Claude’s behavior might not always reflect the constitution’s ideals.

https://www.anthropic.com/constitution

sharts • today at 5:03 PM

One need only look at their leadership and orbiters/relationships of said leadership to know this would always be the case.

giancarlostoro • today at 5:49 PM

> closed models refused to help

Yeah, I've always said that AI isn't AI if it needs safeguards that are so extreme it cannot figure out if something is genuinely bad or not.

lofaszvanitt • today at 6:14 PM

And you believe this nonsense, that you needed teh help of a shitty LLM model and not a real expert on the topic?