Show HN: I made an agent can self-improving while working

(yehuitang0316.github.io)

5 points | by yt1998 12 hours ago ago

3 comments

  • ethan1998 11 hours ago ago

    I tried to implement RSI in my own business, but it is hard to decide when to update harness and when to update model weights.

    • yt1998 11 hours ago ago

      I think it depends on the scale and quality of the data you have. Our project, General Evolution Architecture (Gear), starts with updating the harness and later the model weights and seed tasks for training (Under implementation). Please give it a try. We welcome any feedback.

      • jeff42 11 hours ago ago

        [dead]