Thread

1. maltalex · 1789517911 · focus · HN ↗

   This is a very promising idea - a model that takes arbitrary text input (which can be a complex json), plus a set of questions (yes/no, multiple-choice, or score) and quickly (milliseconds) and cheaply ($0.042/MTok) answers those questions.

   Unfortunately, none of this is explained in the announcement, but the documentation [0] is pretty good.

   [0]: <a href="https:&#x2F;&#x2F;docs.typesafe.ai&#x2F;concepts&#x2F;how-to-build-with-system-one" rel="nofollow">https:&#x2F;&#x2F;docs.typesafe.ai&#x2F;concepts&#x2F;how-to-build-with-system-o...

   1. 18al · 1789542563 · focus · HN ↗

      API example[0] makes it clear how it&#x27;d be used:

        from typesafe_sdk import Choice, Noul, Score, TypeSafeClient
        
        with TypeSafeClient() as client:
            response = client.system_one(
                state={"document": "I was charged twice. Please fix this ASAP."},
                questions={
                    "billing": Noul(instructions="Is this ticket about billing?"),
                    "tone": Choice(
                        instructions="What is the customer's tone?",
                        criteria={"calm": None, "frustrated": None, "angry": None},
                    ),
                    "urgency": Score(
                        instructions="How urgent is this ticket?",
                        criteria=["can wait", "this week", "today"],
                    ),
                },
            )
        
        print(response.nouls["billing"].noul)
        print(response.choices["tone"].choice)
        print(response.scores["urgency"].score)
      

      [0]: <a href="https:&#x2F;&#x2F;docs.typesafe.ai&#x2F;sdk&#x2F;python" rel="nofollow">https:&#x2F;&#x2F;docs.typesafe.ai&#x2F;sdk&#x2F;python

      1. lostmsu · 1789847509 · focus · HN ↗

         [dead]

   2. leobuskin · 1789555896 · focus · HN ↗

      An example with manual combinatorial exclusion in “not_for” field made me cry, this is a wild hybrid of code logic, textual definitions, and AI blackbox. It’s a cool idea, but the “glue” layer is too boilerplate-ish
   3. niutech · 1789920422 · focus · HN ↗

      The concept isn&#x27;t new: zero-shot classification using e.g. Facebook BART has been available for years. And there is already an open source model Laya: <a href="https:&#x2F;&#x2F;laya.convaiinnovations.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;laya.convaiinnovations.com&#x2F;

Unofficial Hacker News client; not affiliated with Y Combinator.