> [others] Output tokens: ~5x more expensive than input tokens.
> [them] Output tokens: FREE (too cheap to meter).
I'm very confused by this.
Introducing System One Models and Jev
21–30 of 513 posts
Re: Introducing System One Models and Jev
#22What is it about the rendering of this page that is so... off? It almost looks like the entire thing is a element.
edit: looks like a framer export where there is a text stroke being applied :|
Re: Introducing System One Models and Jev
#23It 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.
Re: Introducing System One Models and Jev
#24> Extraordinary claims require extraordinary evidence so see below for the receipts. Yes, that’s the kind of attitude I want to see in these model releases
But the evidence is not there...
Re: Introducing System One Models and Jev
#25Earlier quoted context omitted.
Direct link to the Doom video tweet: https://x.com/completeskeptic/status/2099925687465570372
The doom video is also in the article itself (headline: "Doom"). I suppose this is the same video as the one from the parent comment, but I don't know for sure - I don't have a twitter account and the above link doesn't work for me.
[flagged]
Re: Introducing System One Models and Jev
#26Why 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.
Re: Introducing System One Models and Jev
#27um what is going on with the outfit changes in the launch video... https://x.com/CompleteSkeptic/status/2099925682726002904
The whole video seemed generated to me
Re: Introducing System One Models and Jev
#28> Extraordinary claims require extraordinary evidence so see below for the receipts. Yes, that’s the kind of attitude I want to see in these model releases
But the evidence is not there...
Indeed, they talk as skeptics but don’t offer a ton of evidence, other than a couple videos of demos. A live demo would be far more convincing.
Re: Introducing System One Models and Jev
#29This 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…
They have various benchmarks, e.g. how much time it takes them to do wikipedia page -> page games. Jev seems to take the same or fewer hops but in ~10x less time and for ~10x less money.
It's totally reasonable to compare against LLMs doing chain of thought if it gets comparable performance.
Re: Introducing System One Models and Jev
#30Woof, that page is hard to read. I don't understand what they've done to the way text is rendering but it's not great for my eyes.