Thread

1. sheepscreek · 1789606644 · focus · HN ↗

   Haven’t we moved on from these things? Most recent LLMs have been trained on enough long context tasks to have become pretty good at planning. Perhaps with contributions from the harness. In either case, I wouldn’t bother if I were using Codex or Claude Code.

   1. Wazzymandias · 1789609905 · focus · HN ↗

      > been trained on enough long context tasks to have become pretty good at planning

      This is absolutely not true

      1. verdverm · 1789612281 · focus · HN ↗

         if anything in the latest batch, they have been trained to try everything and anything to get a task done, hence their hacking abilities, but also how they go way off the rails when they don't get sufficient context on our human intent for the task

         feels less like planning and more like throwing spaghetti at the wall the moment ambiguity emerges, I really hope the next batch dials it back

      2. thesmtsolver2 · 1789613295 · focus · HN ↗

         Well, they are absolutely pretty good at faking being good at long-horizon planning which is enough to fool a lot of people till things start breaking lol.

         1. vintermann · 1789634190 · focus · HN ↗

            At least for my personal projects, it's enough that they're better than me at long-horizon planning.

Unofficial Hacker News client; not affiliated with Y Combinator.