[mvkel]

> do their nonsense to get headlines

They know what they're doing. It's a playbook. You write scary stuff in the model card to make it look like legitimate whitepaper rEsEarCh, then drip-feed it to the media outlets who make it a headline story. Fear based marketing is the hot trend of the 2020s.

But also, they write literal headlines: https://www.anthropic.com/research/agentic-misalignment

[patcon]

What differentiates this faking/scaring from real risk that's being avoided or mitigated responsibly? And how would you (an outside observer) ever know the difference as something beyond an uninformed hot-take?

Serious question -- I'm not trying to disrespect. Neither you nor I can be properly informed, nor can be anyone else outside the company, as outside observers who lag behind the state of the art as new behaviors emerge, right?

[mvkel]

I was simply responding to the point that Anthropic has some altruistic bent and are trying to downplay the fear, when in fact their entire commercial strategy is to convince society that they alone are qualified to hold the keys.

Being in the Bay Area, you can throw a stone and hit a senior employee of these companies, and they will happily gush about the quirks, policies, and intents inside. All the more reason that they are -not- qualified to weigh in on who gets the nuclear codes.

[killerstorm]

You're confusing PR with marketing. Flaws they find aren't going to convince customers to buy the product. But they need to inform the public of what they doing as it's part of the mission.

I haven't seen media outlets picking up on "agentic misalignment".

The core of your claim is that it's not a legit research. But that's basically a conspiracy theory. We know for a fact that Anthropic employs some of the best people in the industry, including ones who are deeply concerned about safety. Their interpretability research is some of the best. So what's more likely:

* Research is fake and everyone is on it * It's a legit research even if not very interesting

[mvkel]

So OpenAI calling Anthropic out on their fear based marketing is an unqualified statement?

Have -any- of Anthropic's concerns of imminent disaster passed muster?

[killerstorm]

What's "concern of imminent disaster"?

Anthropic said their latest model is good at finding zero-days exploits. That's just empirically true.

They aren't selling vuln search product in an open, so it's not marketing - they are explaining the need for guardrails.

Sam Altman likes to talk shit about competitors, what about it?