Hacker News Reader

A model that was introduced a few days ago that's LLM-based, but instead of producing text, you can ask it questions and it will return decisions. The key thing being that it responds pretty quickly and predictably.

Site: https://typesafe.ai/blog/introducing-system-one-models-and-j...

View on HN

It's a closed model and they claim that it's not LLM-based, so I'm not sure why you are claiming that it is LLM-based.

where is the claim it is not LLM-based? The claim I saw is that it is not chat-based but still text-based (JSON).

In the link of the comment I was responding to, they explicitly say that Jev is not LLM-based:

> Is Jev just a smaller LLM?

> Jev is neither small nor an LLM, hence being off the intelligence Pareto curve.

Sounds like BS for me. Jev is transformed-based, trained on language/texts, it receives text inputs and output text (json).

Jev is a language model. It doesn't matter if it is not a "smaller LLM" or not LLM by some weird definition.

> output text

according to the people who made Jev, it does NOT output text. it's a closed model, so we can't inspect the internals, but i would just take their word for it.

just because the API responds with JSON text, does not mean that the underlying model is generating JSON text.

Yeah, it outputs probabilities over the options you give it. It's basically a generalizable classifier.

Reply on news.ycombinator.com