Hacker News new | ask | show | jobs
by shay_ker 17 days ago
How much do the labs post-train on the harness inputs & outputs? That's a critical piece to understand if a "generic" harness is at all possible
2 comments

https://lucumr.pocoo.org/2026/7/4/better-models-worse-tools/ says already too much to use foreign tools.
I think tools have to be flexible enough to accommodate a range of expected inputs. Even assuming models are trained to supply a particular schema, they are stochastic and randomly output variants regularly. My experience has been that it's better to try to auto-normalize the range of anticipated outputs and make tools as forgiving as possible rather than force an overly strict schema that might not match training data on the model.
I've experimented with completely novel tool call syntaxes combined with ordering and structuring the context differenly, and they seem to have a high tolerance for this stuff. But you always risk losing performance, probably highly unlikely to exceed stock performance across the board.