This makes me kind of nervous for the whole AI thing now. Are people gonna lose their jobs, etc.? so much of the economy is now built on top of LLMs.
Introducing System One Models and Jev
201–210 of 512 posts
Re: Introducing System One Models and Jev
#202Re: Introducing System One Models and Jev
#203This makes me kind of nervous for the whole AI thing now. Are people gonna lose their jobs, etc.? so much of the economy is now built on top of LLMs.
What's different about this particular model that worries you?
Re: Introducing System One Models and Jev
#204Side note: it took me more time than I would like to admit to realize that Diogo Almeida isn’t a satirical version of the name Dario Amodei
Well now I’m rooting for them!
Re: Introducing System One Models and Jev
#205This makes me kind of nervous for the whole AI thing now. Are people gonna lose their jobs, etc.? so much of the economy is now built on top of LLMs.
What's different about this particular model that worries you?
it doesn't require nearly as much compute as normal LLMs. anything depending on increased datacenter and compute spending would be threatened.
Re: Introducing System One Models and Jev
#206There's a whole lot of information on this page that doesn't tell me anything about what this actually is. Can anyone spell out what the architecture is here? They claim it's not an LLM, which I read as "not an auto-regressive token generator". I assume they are still using a transformer, otherwise they would be talking about the thing that's not a transformer, instead of all the fluff on the linked page. But they em…
Sounds like its essentially a generalized zero-shot classifier that takes and option set at runtime and works on unstructured inputs.
you pass in your "prompt" and options (described in natural language) that it can respond with, in addition to your input. it gives back that option set with a probability assigned to each one
Re: Introducing System One Models and Jev
#207Earlier quoted context omitted.
Yeah but what stops it from producing confidently incorrect outputs...
Nothing, but imagine using LLMs for a classification task People out there are so resigned to the models being unreliable that they are really doing things like hallucinating deliberately, and then matching the hallucinations to embeddings - https://softwaredoug.com/blog/2026/08/10/hypothetical-classi... You could do that or you could just... use a model that will never produce unreliable outputs in the first place.
But we're going from "Apple" to "Apple: 99% - trust me". It could still be an image of an orange :)
Re: Introducing System One Models and Jev
#208If we could come up with a system to classify the probabilities across a large number of candidate words (or components thereof) then this could actually be good at producing text, one element at a time. We could call these elements 'tokens' and picking the right one could be called something like 'decoding'. Crazy idea but hear me out...
On a more serious note, it will be fascinating to see how this different spin on modelling inference will create new paradigms or slot into existing ones.
Re: Introducing System One Models and Jev
#209This, 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…
love it. send me an email and i'll try to get you moved up on the list? nathan@typesafe.ai
Re: Introducing System One Models and Jev
#210If it work as good as they say it does, confidence score + really fast response when you want very fast response, basically.. To me it is a crime against humanity to not open source it. Just get the money from cloud inference and cloud agentic sessions or whatever but open source it. This tech, a good harness, a good model provider, and you have basically a AGI building machine.
Golem, if you read this, add me on battle.net (europe) Sansviande#2540 and let's talk. Give me 1 minute.