What's the difference compared to just taking an embedding and feed forward a simple net trained for the task?
Introducing System One Models and Jev
91–100 of 512 posts
Re: Introducing System One Models and Jev
#92This sort of stuff almost sends shivers down my spine, it's like i'm looking 5 years into the future.
There was no "AI Winter"
Re: Introducing System One Models and Jev
#93After much fumbling around with prompts and evals, this is exactly how I am using LLMs in production, to narrowly make choices and return structured data. Any deterministic work gets pulled out of the prompt and my goal is to narrow the model output to be as clearly defined and as minimal as possible.
Jev's focus on structured I/O and confidence scores are game changing. If this does at all what it claims, I think this is going to quickly become the new standard approach for agentic systems.
Re: Introducing System One Models and Jev
#94I 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…
Isn't openrouter the exact opposite of caring about security and privacy? I guess you can choose your provider still? But isn't the point that the lowest bidder is doing inference?
I always setup guard rails so that only zdr providers are used.
Re: Introducing System One Models and Jev
#95Congrats on the release!
Finetuning a language model for decision classification (with probabilities) is already well-understood. What specifically changes in the training objective with RLCD? Are its benefits isolated from Jev’s new architecture/parallelism?
Re: Introducing System One Models and Jev
#96First, 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…
> Jev can only generate structured output, right? This is probably super useful for classification/routing/scoring,
My first thought was that it would be ideal for robotics? As in control of limbs, general planning, route finding, etc.
Re: Introducing System One Models and Jev
#97Interesting concept, I can't see a reason to use a generalist classifier over an api rather then just training my own? If it was open weights I would probably mess around with it.
Re: Introducing System One Models and Jev
#98[dead]
Re: Introducing System One Models and Jev
#99It 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)
I see this super interestingly as the "subconscious" to the llms "conscious" for lack of better terms. I'm super interested in this for broad and rapid decision making in the context of consumer agents so will be signing up for sure.
Re: Introducing System One Models and Jev
#100First, 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…
When they say "can't hallucinate" they mean they produce a confidence value for every result, so you could see for example it has 0.1 confidence, and you can disregard the result - that'd be different from hallucinating where it believes it's correct