So in theory you could feed it incomplete text, and then ask it for the probabilities of what the next character could be?
I think the joke here is getting missed
Introducing System One Models and Jev
111–120 of 512 posts
Re: Introducing System One Models and Jev
#112First, 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
that's right, but because these models are probabilistic, it's also possible to be confidently wrong (and all future models will be smarter still and still have that possibility)
Re: Introducing System One Models and Jev
#113First, 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…
I don’t think it’s misleading if you compare on the use cases they suggested. It’s faster and cheaper (no idea if higher quality), so it’s immediately interesting for certain things.
And if you buy their RLCD claims, this might be even better than huge models that know a bunch of irrelevant things.
Re: Introducing System One Models and Jev
#114This sounds good but so far all claims just sound like marketing terms. I'd love to see real proof. e.g. "RLCD" and "parallel sampling" have nothing to back it up. also "70-500ms vs 3-329 seconds" are apples-to-oranges unless the LLM baseline is doing comparable work (e.g., long chain-of-thought). If Jev is skipping generation entirely for a narrow structured task, of course it's faster. Nonetheless i want this to be…
love that you love the manifesto! letting the first batches off the waitlist now, but we do have some early users describing their experience (https://x.com/danshipper/status/2099947471518474522)
Re: Introducing System One Models and Jev
#115First, 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
Technically speaking when you send the prefix “The capital of France is “ into an LLM it will also produce probabilities across its whole vocabulary.
Re: Introducing System One Models and Jev
#116Congrats on the launch! What's different between Jev and Microsoft's Guidance package? https://github.com/guidance-ai/guidance Is it a diffusion generator under the hood?
Re: Introducing System One Models and Jev
#117Earlier 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)
For many day-to-day computing use cases, Jev seems far better suited than an autoregressive language model, if for no other reason than it is not wasting compute thinking about anything other than how to spit out a decision. Do you have an architectural explainer yet for Jev or are you holding that close to your chest and letting the magic rip for now?
architecture is close to the chest for now, but we have talked about writing a paper
I don't want to shill my blog too much, but I will say data is probably far most interesting than architecture: https://www.completeskeptic.com/p/the-bitterest-lesson
Re: Introducing System One Models and Jev
#118Is there a downloadable technical report somewhere?
Re: Introducing System One Models and Jev
#119> Input tokens: $0.042 / MTok ($42 per billion tokens). > Output tokens: FREE (too cheap to meter). Insane. The video demos are really compelling, in particular the speed. > Structured outputs slot into ordinary software as fuzzy decision rules: classify, route, score, extract, or branch where hand-written logic is too brittle. The surrounding code constrains their freedom, making them easier to compose into reliable…
thanks a ton!
constrained decoding (OpenAI-style structured outputs) make models dumber unfortunately - the short+dense version is that simply masking logits is insufficient because if ever a model was assigning probability to an invalid token, the model is by definition confused. you'd be better off erroring IMO
Re: Introducing System One Models and Jev
#120First, 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…
I'm biased but I wouldn't call it misleading - generating text is super awesome and flexible, (we describe that in the blog post - and I personally use string models all the time) but it's true you pay a high tax for autoregressive generation > Also "can't hallucinate" seems wrong? Sure, it can't emit an invalid type, but it can still emit a completely wrong valid value. that is likely true of all ML! perhaps we coul…
From a quick look at this it looks like it could easily generate natural language text by following a structured representation like UMR (Uniform Meaning Representation) or the similar representation the Abstract-Wikipedia folks will be working on for generic encyclopedic text (which will be heavily informed by Universal Dependencies). These are basically linguistically principled and frame-based counterparts to a programming language AST, that can be then converted to natural language (in a broadly language-independent way, to the extent that semantics and pragmatics make that feasible) via some sort of NLG rendering.
(To be clear, this one raw model does not support outputing a full AST directly - it wants to output "choice" among fixed options, "score" on a sliding scale, or a true/false answer (all of these with confidence scores attached), so building the AST/structure would be a code-driven (or even perhaps outside LLM-driven in some more challenging cases) multi-step affair where the model would essentially be playing a "game" of building the structured output step by step and getting a revised partial state back. But one could expect this to lead to interesting results.)