• ThirdConsul@lemmy.zip
      link
      fedilink
      arrow-up
      7
      ·
      edit-2
      15 hours ago

      Actually I think it’s doing well? The language to language rewrite is actually a strong suit of LLMs, as long as there is extensive years worth of tests to check rewrite behaviours.

      I don’t have practical use cases for that strong suit though.

      Oh, and bun seems to be dead now with 2.5k open PRs.

      And merge to main takes over an hour

      • Eager Eagle@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        14 hours ago

        It was higher sure, but anthropic also has some of the most expensive models out there. That cost could be 5x-10x less just by going with cheaper model providers (if one were to pay the API costs, not the case for bun).

        bun 1.4 was released 3 weeks ago, btw

        • ThirdConsul@lemmy.zip
          link
          fedilink
          arrow-up
          1
          ·
          13 hours ago

          That cost could be 5x-10x less just by

          My point was that it was cost of model rewrite by agents + 3 months worth of coding by lots of people.

          5k open PRs atm + 3.5k open issues. I have no idea what is the state of Bun right now, but I am not confident in it.

          • Eager Eagle@lemmy.world
            link
            fedilink
            English
            arrow-up
            1
            ·
            edit-2
            13 hours ago

            I don’t think there was a lot of people working on the rewrite. Most PRs are from bots. Original estimates for a manual rewrite were a small team working for a year or so, which puts total costs over $1M. Even doubling the token cost estimates, it was still cheaper than doing it manually by a factor of 2x-3x