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

31–40 of 512 posts

Re: Introducing System One Models and Jev

#31

Post by vatsachak »

ramon156 wrote: post #23
vatsachak wrote: post #13

It could be used for coding if you gave it an AST. If you work at TypeSafe please try this. Side note: This is probably how LLMs would perform with better encoders and next-latent prediction, so eventually those will beat this architecture out. Still amazing though.

I've implemented tree-sitter in pi before, and while it works, I have no real proof it saves me tokens, or is more accurate. I think a better implementation is a model that's trained for AST's, not just "use tool, see what happens". I'd love to do research on this when I have the time.

Cool project!

That's what I was insinuating through "better encoder"; the model creating more efficient representations of ASTs using something like JEPA

Re: Introducing System One Models and Jev

#32

Post by vatsachak »

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…

It's not an LLM though it's a frontier model on structured data

Re: Introducing System One Models and Jev

#33

Post by oblio »

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…

The thing is, in this climate it's hard to believe such tech will remain secret for long.

So, assuming this is not vaporware, this would raise the tide for everyone because it shows what's possible.

Re: Introducing System One Models and Jev

#34

Post by jceg »

> We deliberately chose not to publish performance against public benchmarks. In fact, we plan to only have one-off evals when we make product updates.

lol, I bet they would publish them if their score on those benchmarks were good.

Re: Introducing System One Models and Jev

#35

Post by oblio »

andai wrote: post #26

Why did they pick the name System One? It's not really explained what "System One tasks" and "System One shaped queries" are. Things that need a fast response? Does this imply it's a very small model? I couldn't find anything about the model itself.

Maybe: https://thedecisionlab.com/reference-guide/philosophy/system...

Re: Introducing System One Models and Jev

#37

Post by hunterbrooks »

oblio wrote: post #35
andai wrote: post #26

Why did they pick the name System One? It's not really explained what "System One tasks" and "System One shaped queries" are. Things that need a fast response? Does this imply it's a very small model? I couldn't find anything about the model itself.

Maybe: https://thedecisionlab.com/reference-guide/philosophy/system...

Bingo. It's a Psychology term for the part of our brain that reacts instinctively rather than thoughtfully and logically

Re: Introducing System One Models and Jev

#38

Post by jawns »

I could see this being fantastic for classification tasks. Last year I shifted from using LLMs for bulk data classification tasks (1M transcripts) to generating embeddings and categorizing based on cosine similarity. It saved a ton of costs and time, but wasn't as accurate as LLMs. This seems like it can give me Terra-level classification ability with the cost/speed I need.
Post reply on HN