Introducing System One Models and Jev

I’m not understanding what this is. It’s a faster cheaper LLM?

this might finally be smart enough and fast enough for jarvis. hard to feel like iron man when your assistant takes 8 seconds to decide to pause your music

a) Is this available on Bedrock? b) Does it support structured outputs? c) What about trying it out?

Is there a bottleneck which would hinder putting this architecture in charge of a humanoid? Would it be able to operate continuously, for example in conjunction with an LLM for long-term reasoning? Doom seemingly works extremely well.

oooooh it can play Doom!

forget LLM benchmaxxing sidequests, I'm sold on the real benchmark

Parallel inference where you don't want a subagent seems niche. But there is a lot of random things where businesses ultimately want some kind of score instead of generating something.

I think the interesting thing would be seeing if prompt injections still work with this kind of model.

What is it about the rendering of this page that is so... off? It almost looks like the entire thing is a <canvas> element.

edit: looks like a framer export where there is a text stroke being applied :|

Am I the only one struggling to parse the distinction System One (the system/harness?) and Jev (the model?)?

Looks like a great model for NLP.

this is interesting, so not an LLM but can be used in these use cases that LLM's have been shoehorned into

https://docs.typesafe.ai/concepts/use-case-map

my sons name is also Jev

"While Jev gives up string generation, it’s optimized for structured outputs and can’t hallucinate"

Ouh! Any open weights models that can do this yet?? If not, how much longer? I have a Mac Studio coming soon.

> Outputs

> LLMS > Strings / generated text. Strings are flexible and can be anything: chat responses, code, hallucinations, refusals, or even type-safe structured values. To be used by software, responses need to be parsed + validated. There is also always some risk that the AI goes off the rails.

> Jev > Type-safe structured values. Possible outputs and structure are defined in advance. The model never makes type errors. All answers are accompanied with calibrated probabilities and confidence scores.

I mean, this isn't even remotely comparable to LLMs so why compare? Also, why are they bringing up AGI given there approach is so restrictive that what they're building literally cannot have the creativity required for AGI? The video is 100% marketing slop...

The bulk of the application of LLMs is that they generate reasonably reliable text which doesn't need to be defined in advanced. I'm sure there is a niche for this and congrats to the team, but please let's not hype this as if it's the next big thing in AI...

If this is true means, AI Stock bubble burst. (For good)

It looks like a specialized encoder-only(-ish) transformer with scalar and ordinal output heads. Acausal in effect, maybe? Probably not even autoregressive?

I'd use this as a tool an LLM can use for specialized tasks. It's not AI in itself.

[dead]

[dead]

[flagged]

[dead]

[dead]

TLDR: Like an LLM, the input is a string, but the output is not a completion. The output is a ranking of elements from a certain enum (e.g, [Yes/No], [A/B/C/D]). They use a technique called Reinforcement Learning for Calibrated Decisions (RLCD) instead of RLHF. Also, inference is a lot faster.

https://docs.typesafe.ai/primitives has a much better explanation

[dead]

[dead]

[dead]

Finally a fast solution to isOdd / isEven :) /s

If this is true, then AI Stock Bubble burst (for Good)

"is this the real thing or is just fantasy"

Cool I guess. Definitely not worth the 1000+ points though.

This makes me kind of nervous for the whole AI thing now. Are people gonna lose their jobs, etc.? so much of the economy is now built on top of LLMs.