Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Introducing System One Models and Jev

typesafe.ai

Post reply on HN
Print view View original

71–80 of 513 posts

Re: Introducing System One Models and Jev

#71

Post by dennisy »

adroitboss wrote: post #61

I am positive I know exactly how this works, I made something similar a few months back. But the problem is without generation you are extremely limited in the use cases. And while the model can't hallucinate, it can still be wrong. It just can't make up data.

Are you able to share how it works in that case?

Re: Introducing System One Models and Jev

#73

Post by CompleteSkeptic »

moffers wrote: post #39

So is it a structured data-based language model? Or is there a model and a harness? Hopefully they’ll open up and explain more.

it is just a model, no harness yet ;)

it is a structured data model, but technically not a language model (it doesn't generate language)

Re: Introducing System One Models and Jev

#74

Post by ajmurmann »

cheeze wrote: post #44
mushufasa wrote: post #18

I 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?

You can set privacy requirements and define an allow list. To me the main value prop is that I get one bill for all models and can quickly try new models without signing up anywhere or changing my code. Oh! Also you can pass an array of models and if the first provider is down it automatically falls through to the next provider. More useful than it should be...

Re: Introducing System One Models and Jev

#76

Post by CompleteSkeptic »

charcircuit wrote: post #58

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.

we have played with this! the fascinating thing we've found so far is that adversarial examples for our model are quite different from that of LLMs so that they work even better together

Re: Introducing System One Models and Jev

#77

Post by yieldcrv »

simianwords wrote: post #55
BoorishBears wrote: post #42

Earlier quoted context omitted.

Did you see the video where it plays Doom, it made it click for me

BTW it was not multi model playing doom, it was passing structured input and getting structured output. Its not what I thought: frames of video passed and real time game play.

so what? put an LLM on Cerebras and get its responses faster, and put Jev on Cerebras and gets its responses even faster

Re: Introducing System One Models and Jev

#78

Post by CompleteSkeptic »

Gecko4072 wrote: post #48
hunterbrooks wrote: post #12

um what is going on with the outfit changes in the launch video... https://x.com/CompleteSkeptic/status/2099925682726002904

Can't tell if they're just having fun or if it is ai-generated. On the verge of not being able to tell. Voice sounds a little synthetic.

definitely not AI-generated - this is my real wardrobe

we also thought the voice at the end was AI-ish, but apparently that's a real voice actor but slightly sped up

Re: Introducing System One Models and Jev

#79

Post by initsecret »

ambicapter wrote: post #60
quotemstr wrote: post #45

Earlier quoted context omitted.

They're not doing autoregression, so all the outputs are computed in one big forward pass. Very cheap.

I think OP is confused about "others" vs "them".

they’re talking about two totally different things, right?

Re: Introducing System One Models and Jev

#80

Post by petesergeant »

This is basically a zero-shot classifier that can accept raw text (or structured text) as an input, and is able to classify that text as accurately (they claim) as a frontier-level LLM. I have workflows this would be useful for, looking forward to it showing up on OpenRouter.
Post reply on HN