News for hackers. Stuff that matters.
Re:Notes on OpenAI's new o1 chain-of-thought models by flanked-evergl on Friday September 13, 2024 @06:04AM (#41529687)
> The failure is in how you're using it.

People, for the most part, know what they know and don't know. I am not uncertain that the distance between the earth and the sun varies, but I'm certain that I don't know the distance from the earth to the sun, at least not with better precision than about a light week.

This is going to have to be fixed somehow to progress past where we are now with LLMs. Maybe expecting an LLM to have this capability is wrong, perhaps it can never have this capability, but expecting this capability is not wrong, and LLM vendors have somewhat implied that their models have this capability by saying they won't hallucinate, or that they have reduced hallucinations.

Re:Notes on OpenAI's new o1 chain-of-thought models by vingt_regards on Friday September 13, 2024 @06:26AM (#41529819)
> the distance from the earth to the sun, at least not with better precision than about a light week

The sun is eight light minutes away.

Re:Notes on OpenAI's new o1 chain-of-thought models by flanked-evergl on Friday September 13, 2024 @07:11AM (#41530052)
Thanks, I was not sure if it was light hours or minutes away, but I knew for sure it's not light weeks (emphasis on plural here) away. I will probably forget again in a couple of years.
Re:Notes on OpenAI's new o1 chain-of-thought models by arb_ on Friday September 13, 2024 @10:00AM (#41531342)
Empirically, they have reduced hallucinations. Where do OpenAI / Anthropic claim that their models won't hallucinate?
Re:Notes on OpenAI's new o1 chain-of-thought models by flanked-evergl on Saturday September 14, 2024 @06:55AM (#41538918)
One example:

https://www.theverge.com/2024/3/28/24114664/microsoft-safety...

> Three features: Prompt Shields, which blocks prompt injections or malicious prompts from external documents that instruct models to go against their training; Groundedness Detection, which finds and blocks hallucinations; and safety evaluations, which assess model vulnerabilities, are now available in preview on Azure AI.

Re:Notes on OpenAI's new o1 chain-of-thought models by simonw on Saturday September 14, 2024 @07:59AM (#41539245)
That wasn’t OpenAI making those claims, it was Microsoft Azure.
Re:Notes on OpenAI's new o1 chain-of-thought models by flanked-evergl on Tuesday September 17, 2024 @05:28AM (#41565927)
I never said it was OpenAI that made the claims.