alt Hacker NewsIf you saw the Claude Code leak, you’d know the harness is anything but simple. It’s a sprawling, labyrinthine mess, but it’s required to make LLMs somewhat deterministic and useful as tools.
Replies
girvo • yesterday at 9:47 PM
That’s also because of how Claude Code was written. It doesn’t have to be that way per se.
xstas1 • yesterday at 7:59 PM
Hypothesis: it's a sprawling, labyrinthine mess because it was grown at high speed using Claude Code.
➕ show 1 reply
It's pretty easy to get determinism with a simple harness for a well-defined set of tasks with the recent models that are post-trained for tool use. CC probably gets some bloat because it tries to do a LOT more; and some bloat because it's grown organically.