It seems like the docs[0] are a better explanation? The comparison to llm tokens is kinda confusing.
It looks like the model takes as input a state (structured text? not sure if multi-modal) and a question (as a "Choice", "Score", or "Noul") with some additional augmentations possible. Then outputs the question's answers as appropriate (e.g. a choice, accompanying probabilities, confidence).
Edit: On the AI primer page, it looks like they do the RLCD on a pre-trained base model?
I do agree that the comparison to LLM tokens is hard to understand (also because output tokens are not comparable).
But yes, text or structured state (like a JSON with multiple pieces of text in) -> decisions out (e.g. choice maps to "match" statement, "score" maps to sorting, "noul" short for bernoulli maps to if-statements)
Hi - first congratulations, System One looks really promising.
The Doom demo really help me, at least, to understand how System One differs from LLMs. However the first demo (Side-by-side demonstration) - I'm struggling to understand what is going on here!
I was confused at first too, but it makes more sense when you read about their primitives. E.g. <a href="https://docs.typesafe.ai/primitives/noul" rel="nofollow">https://docs.typesafe.ai/primitives/noul
The demo is showing System One producing its output in parallel very quickly and for little cost compared to an LLM generating its answers token-by-token. The "noul" type is used to evaluate a yes/no question and return the probability that the answer is yes.
So this demo is showing System One offering much more nuanced responses and specific probabilities compared to an LLM's more crude responses (e.g. LLM shows "true" or "false" compared to "0.9" or "0.07" probabilities that the answer to some question is true).
big_toast · · focus · HN ↗
It looks like the model takes as input a state (structured text? not sure if multi-modal) and a question (as a "Choice", "Score", or "Noul") with some additional augmentations possible. Then outputs the question's answers as appropriate (e.g. a choice, accompanying probabilities, confidence).
Edit: On the AI primer page, it looks like they do the RLCD on a pre-trained base model?
[0]:<a href="https://docs.typesafe.ai/concepts/system-one" rel="nofollow">https://docs.typesafe.ai/concepts/system-one
CompleteSkeptic · · focus · HN ↗
I do agree that the comparison to LLM tokens is hard to understand (also because output tokens are not comparable).
But yes, text or structured state (like a JSON with multiple pieces of text in) -> decisions out (e.g. choice maps to "match" statement, "score" maps to sorting, "noul" short for bernoulli maps to if-statements)
Flere-Imsaho · · focus · HN ↗
The Doom demo really help me, at least, to understand how System One differs from LLMs. However the first demo (Side-by-side demonstration) - I'm struggling to understand what is going on here!
davideg · · focus · HN ↗
The demo is showing System One producing its output in parallel very quickly and for little cost compared to an LLM generating its answers token-by-token. The "noul" type is used to evaluate a yes/no question and return the probability that the answer is yes.
So this demo is showing System One offering much more nuanced responses and specific probabilities compared to an LLM's more crude responses (e.g. LLM shows "true" or "false" compared to "0.9" or "0.07" probabilities that the answer to some question is true).