‹ BackHN Continuity

Thread

Introducing System One Models and Jev

1989 points · 520 comments · albelfio

  1. futurisold · · focus · HN ↗
    This, combined with contracts, could make a lot of things so much fun now!

    For those who don&#x27;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: <a href="https:&#x2F;&#x2F;leoveanu.com&#x2F;2025-03-01-dbc&#x2F;" rel="nofollow">https:&#x2F;&#x2F;leoveanu.com&#x2F;2025-03-01-dbc&#x2F; . Contracts are a core feature of SymbolicAI ever since. The community seems to have loved it too (<a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=44399234">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=44399234).

    I think I&#x27;m starting to glimpse the implications and it&#x27;s gonna change agentic workloads if it holds up to scrutiny. It&#x27;s too early for me to tell anything other than jot down some rough thoughts.

    In short, you get blazingly fast semantic branching you can use in control flows. For contracts, I can now directly take the data model that you have to design and convert it into Jev&#x27;s expected format. Or I can use Jev for semantic branching in postconditions.

    If my understanding is correct, that should be doable, but I need to think more about it. It could be that with Jev I can finally “compile contracts” and better chain them into workflows, which is something I always wanted but didn&#x27;t know how to do properly.

    Eager to test. On the waiting list.

    1. 3abiton · · focus · HN ↗
      Why wait, if there is already a similar implementation a year ago, and it&#x27;s fully open source: dataset, paper, repo etc ... The idea is not new.

      <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=49736660">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=49736660

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.