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

361–370 of 512 posts

Re: Introducing System One Models and Jev

#361

Post by hobofan »

ajmurmann wrote: post #74
cheeze wrote: post #44

Earlier quoted context omitted.

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...

That's still ultimately privacy by contract (where you have to trust the inference providers to uphold their end of the deal), rather than privacy by design.

Re: Introducing System One Models and Jev

#362

Post by ygouzerh »

Flere-Imsaho wrote: post #96
jacobgold wrote: post #81

First, 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.

That's a great point! It quite looks like the System 1 model of Physical Intelligence

Re: Introducing System One Models and Jev

#363

Post by baq »

eru wrote: post #335
jubilanti wrote: post #304

Earlier quoted context omitted.

Correct, they have not made a universal all-knowing omniscient oracle, which is what would be required for "can't hallucinate".

That seems like a weird standard. I would be happy enough with: only produces what it can verify with sources. If you eg try to remember a court case (ie produce the reference via LLM token generation only), it's easy enough to check with your data whether it really exists. Similar for following links and other references. If your data or sources are wrong, obviously your report about them will be wrong. But I wouldn…

There isn’t a single human in this world and hasn’t ever been that meets your happy-enough standard. Make of it what you will.

Re: Introducing System One Models and Jev

#364

Post by baq »

spencerflem wrote: post #332
jubilanti wrote: post #304

Earlier quoted context omitted.

Correct, they have not made a universal all-knowing omniscient oracle, which is what would be required for "can't hallucinate".

Not to be tooo pedantic, but a bot that assigned 0 confidence to everything wouldn’t hallucinate. A calculator either gets the right answer or doesn’t answer. It wouldn’t have to be all knowing as long as it knew perfectly what it doesn’t know

A quantum calculator answers in distributions.

Re: Introducing System One Models and Jev

#365

Post by kevmo314 »

tylermarques wrote: post #125

We had early access and found it to be pretty useful. Having a second form of verification, where you can ask multiple questions (in the form of Nouls) raised our confidence in the outputs of other models. [0] IMHO This type of model works incredibly well in concert with LLMs, not as a replacement. [0] https://goodstartlabs.com/research/verification-is-the-bottl...

Don't your numbers suggest DeepSeek V4.1 Flash, for $100 more, gets you to slightly better agreement?

Re: Introducing System One Models and Jev

#366

Post by rana3g »

nullbio wrote: post #354
latteren wrote: post #341

Looking at the example Jev use cases, it almost feels like Jev's incredible cost/task can make it competitive as a generalized "poor man's ranking" algorithm that can be useful for lean startups or any fast paced development org. I need to rank 1000 articles and pick the 5 most relevant for the user? Jev. I need to audit and strip out content because my user is affected by regional privacy laws (without hallucinating…

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

Re: Introducing System One Models and Jev

#367

Post by flowerboy-t »

do you all see the use cases being similar to what you might use Fastino's Gliner models for? i see similar differentiation from general purpose LLMs in the sense that they can take natural-language input and return outputs adherent to a user-defined schema.

https://fastino.ai/blog/gliner2-5-span-free-information-extr...

im thinking about how well Jev could be used to replace a current LLM-as-Judge evaluation workflows, specifically on chat transcript data (think ~1,500 tokens) i wonder if the reasoning usually required pushes it a bit out of scope. didnt see anything published about constraints on the state size, so would be curious to hear about that.

Re: Introducing System One Models and Jev

#368

Post by suprfnk »

wg0 wrote: post #319
cfowles wrote: post #268

Wasn't really till seeing this home assistant demo they have ( https://www.loom.com/share/18c4dbcf8db546dfb2d7f2ef018e78e4 ) that the value really clicked for me. Seems really cool.

That's good. Side note - just like most people don't need an intelligent personal assistant to manage and respond their emails and book their flights, most people also don't need smart homes. Century old toggle switches are more than enough in a 3 room apartment or 5 room house unless you have a mention.

Need is a big word. Convenience is also a factor.

We have 8 light buttons in our living room/dining room/kitchen space. It is very convenient to us that we have 1 button for turning all of them on/off at the door to upstairs (at night turn off all lights and go to bed upstairs, in the morning come downstairs and turn on all lights) - but also have 1 on/off button near our back door for when we leave/come home.

Next to that: on/off toggles a schedule where the lights are bright and cold-ish by day, and low and warm by night without us having to manually adjust each light every hour or something.

Again, need is a big word. But it's very convenient and pleasant.

Re: Introducing System One Models and Jev

#369

Post by sreekanth850 »

jacobgold wrote: post #81

First, 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…

[flagged]

Re: Introducing System One Models and Jev

#370

Post by eru »

baq wrote: post #363
eru wrote: post #335

Earlier quoted context omitted.

That seems like a weird standard. I would be happy enough with: only produces what it can verify with sources. If you eg try to remember a court case (ie produce the reference via LLM token generation only), it's easy enough to check with your data whether it really exists. Similar for following links and other references. If your data or sources are wrong, obviously your report about them will be wrong. But I wouldn…

There isn’t a single human in this world and hasn’t ever been that meets your happy-enough standard. Make of it what you will.

It's not a binary thing. You can get closer or further away from that standard.

And humans also behave differently in different contexts. A conversation at the pub has more such hallucinations than a formal deposit in court. For the latter, a good lawyer will look at her shoes, when you ask him what colour her laces are.

Post reply on HN