Thread

1. ttoinou · 1790037430 · focus · HN ↗

      Before editing each agent publishes an intent and the scopes it will change, with the operation it plans to complete on each one.
   
   

   But we don't know in advance what we will need to change in our current task. And even if we did, there are always side effects.

   1. naw103 · 1790040223 · focus · HN ↗

      You're right when the agent starts with a plan and no file list and the files only exist after edit, but the way I designed Foremerge to work, it works anyway. The initial intent does not have to be complete, it just has to be right about any destructive parts. That is why Foremerge works by declaring intent as prose, not as a file list or methods. The agents them selves determine if something conflicts based on the signals Foremerge returns. It only asserts a HIGH warning on declared scope and only a HIGH signal blocks acceptance (to avoid false possitives based on prose alone). The declaration can change at any point and the auto installed skills into the agents encourage such (the initial intent is released by the agent and the new intent is committed)

      1. ttoinou · 1790041654 · focus · HN ↗

         I doubt this can really be deterministic, but maybe this is where Jev models can be useful

         1. naw103 · 1790042580 · focus · HN ↗

            You might be surprised, it works exceptionally well. If you decide to give it a shot and run into any issue feel free to reach out to me with any feedback.

            ... and Jev is a sore point for me right now lol we have been training our own decision intelligence model, Corgen, for the last year and a half. We're already using it in GPTree but havn't released it to the public yet. Im actually in the process of running it against JevBench right now to see how it stacks up.

Unofficial Hacker News client; not affiliated with Y Combinator.