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

341–350 of 512 posts

Re: Introducing System One Models and Jev

#341

Post by latteren »

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)? Jev.

I need to surface the 3 funniest media comments that match the user's sense of humour? Jev.

Re: Introducing System One Models and Jev

#342

Post by zergrush »

BoorishBears wrote: post #42
ramon156 wrote: post #19

This 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…

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

i've seen it play minecraft as well, what im not sure here is what is the thing that produces the JSON and keeps track of the objects

can jev play battlefield six for example

Re: Introducing System One Models and Jev

#344

Post by _davide_ »

This is too much for me. ML playing doom was a thing since before LLMs, decisions tree were always insanely and no one ever used then anyway, i can't see anything new in this yet everyone is treating this as a revolution. This technology was always there and quite easily accessible all along.

Re: Introducing System One Models and Jev

#345

Post by paraschopra »

I'm trying to understand what difference does this make over LLMs.

LLMs are universal simulators, their latents model the world. So I bet if you compare their logprobs with probabilities output by this model, it will be highly correlated.

Someone should do this quick experiment. I bet there won't be enough of a meaningful difference.

Re: Introducing System One Models and Jev

#346

Post by Gecko4072 »

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…

Wonder if this could lead to better recommendation algorithms.

Re: Introducing System One Models and Jev

#348

Post by jbotz »

AdieuToLogic wrote: post #338
futurisold wrote: post #172

This, combined with contracts, could make a lot of things so much fun now! For those who don't know (which is probably everyone but me), I ported the design-by-contract pattern in Python and combined it with LLMs. This was early 2025. I originally wrote about it here: https://leoveanu.com/2025-03-01-dbc/ . Contracts are a core feature of SymbolicAI ever since. The community seems to have loved it too ( https://news.y…

[flagged]

Judgemental much?

GP's first sentence isn't arrogant (at worst displaying a bit of false humility) because it's saying everyone but him doesn't know about a thing he did. Your second quote you apparently mis-parsed because of a minor English error (he should have said "to Python" rather than "in Python"), but to me it was pretty clear what he meant.

Re: Introducing System One Models and Jev

#349

Post by bigglebear »

bigglebear wrote: post #227
alfalfasprout wrote: post #173

Earlier quoted context omitted.

How is this not a frontier model? It's bleeding edge in its own niche. It's not a frontier LLM; however, applicable to many of the things people use LLMs for.

It's nothing like a traditional LLM and so should not be compared to one. It's a heavily constrained, tiny model that can only produce a probability score or a yes/no answer over pre-defined selections. It has no long-context capacity. I mean, imagine comparing this thing to Astra, it's hilarious. They don't even tell you what the max input size is, and they only allow 10 possible answers to choose from for the Choic…

Well, not quite a week: https://x.com/harshagundal/status/2100044305536889015 - apparently it took him 2 hours.

Re: Introducing System One Models and Jev

#350

Post by Gecko4072 »

postalcoder wrote: post #179

This has the potential to be huge for computer use. OpenAI has been teasing how fast computer use is with their models running on Cerebras chips but the difference here is a burning hole in your pocket.

Like which elements to select? Similar to the doom and wikipedia runs?
Post reply on HN