a) Is this available on Bedrock?
b) Does it support structured outputs?
c) What about trying it out?
Introducing System One Models and Jev
391–400 of 512 posts
Re: Introducing System One Models and Jev
#392Earlier quoted context omitted.
Guess I'm a bit less impressed seeing that for some of the more intelligent driven+action work -- splitting requests in the video -- they had to kick out to an anthropic model.
Haiku, to rewrite a sentence as two discreet commands. I agree that it was notable that they delegated to an existing LLM, but I don't think it detracts much from the value proposition (not yet proven) of their demo.
Agreed but is it much easier to deal with if you need to have all of these sub processes integrated? How does one know when you need to reword a request? What if Anthropic then has a type error, then debugging that just got harder.
Re: Introducing System One Models and Jev
#393It seems like the docs[0] are a better explanation? The comparison to llm tokens is kinda confusing. It looks like the model takes as input a state (structured text? not sure if multi-modal) and a question (as a "Choice", "Score", or "Noul") with some additional augmentations possible. Then outputs the question's answers as appropriate (e.g. a choice, accompanying probabilities, confidence). Edit: On the AI primer pa…
CEO here - that is right! I do agree that the comparison to LLM tokens is hard to understand (also because output tokens are not comparable). But yes, text or structured state (like a JSON with multiple pieces of text in) -> decisions out (e.g. choice maps to "match" statement, "score" maps to sorting, "noul" short for bernoulli maps to if-statements)
Small request, can we get an explanation of the naming of "noul" in the docs[0]. I tried googling, and searching the docs and didn't understand why it was called that.
(I'd also argue something like p_yes or just probability might be a simpler name, but I'm sure there's a better reason behind Bernoulli maps).
Re: Introducing System One Models and Jev
#394I am not an expert in this domain but as an engineer-turned-researcher, this looks a lot like GliNER with a fitting harness.
This is something I focus on in a bunch of my experiments - how to get immense value out of tiny models (Great to see this and I hope this is a lot on top of what is already openly available.
Re: Introducing System One Models and Jev
#395Earlier quoted context omitted.
More like: I need to ...? -> Open-weight model. I'm sure someones working on this as we speak using an open-weight LLM base (Qwen or something would be a perfect fit). This sort of task is a perfect fit for a very small model capable of semantic parsing. You can get away with a LOT less parameters without all the autoregressive generation and long-context reasoning.
you don't say - https://huggingface.co/harshatheg/Qwen-2.5-1B-RLCD
Crazy, looks like this was just published a few hours after the TypeSafe post!
Re: Introducing System One Models and Jev
#396Always exciting to see people working on novel models, rather than the Nth version of the same slightly tweaked LLM.
I'm very curious how much ressources are needed to run such a model. This could be a complete game changer for local applications.
Re: Introducing System One Models and Jev
#397I would love for things like this to be accessible via hubs like open router or AWS bedrock. It's hard to justify adding new model vendors directly with all the heightened concerns about privacy and security, but if bold new capabilities are added to a centralized already-vendor like AWS, technical people can adopt them without going through a whole compliance/purchasing/vendor review process. And an extra middleman…
I think the trouble is that Typesafe APIs don't fit into the normal OpenAI-style API that every other regular LLM provider users. You're not just providing unstructured text and getting unstructured text back. It would take a different request and response format than every other model on Open Router. Though you could shoe-horn it in some way, it'd be hacky. But agreed it'd be very useful to see it deployed on other…
It can be shoehorned to work with OpenAI's newer Responses format.
Re: Introducing System One Models and Jev
#398[dead]
Re: Introducing System One Models and Jev
#399First, congrats to the team on launching something genuinely interesting and new. Seems like a more accurate title would be "Jev: Trading general purpose generation for fast typed inference" or something like that. This is interesting, but the speed comparison seems misleading? A generative model that can output code in a Turing-complete language can do anything a computer can do. Jev can only generate structured out…
> Assuming there's no funny business, the Doom demo is cool. The Doom demo seems very funny business. They're not feeding it video, they're feeding it a text description of what's going on in the game. It's not reading pixel data. I think LLMs would play a lot better with that input too but Jev does seem to have a huge speed advantage; I don't know if the other models could do that in real-time.
In a case like this it still seems more appropriate to encode that data in tabular form and use a tabular foundation model
Re: Introducing System One Models and Jev
#400Earlier quoted context omitted.
CEO here - that is right! I do agree that the comparison to LLM tokens is hard to understand (also because output tokens are not comparable). But yes, text or structured state (like a JSON with multiple pieces of text in) -> decisions out (e.g. choice maps to "match" statement, "score" maps to sorting, "noul" short for bernoulli maps to if-statements)
Small request, can we get an explanation of the naming of "noul" in the docs[0]. I tried googling, and searching the docs and didn't understand why it was called that. (I'd also argue something like p_yes or just probability might be a simpler name, but I'm sure there's a better reason behind Bernoulli maps). [0] https://docs.typesafe.ai/primitives/noul#noul
Im going to guess bernoulli