Even prior to Fable, Claude Code had reached the point of accelerating our coding work dramatically. That was a pretty recent development; prior to the last few months, LLM coding contributions were relatively marginal for the sort of coding problems we work on. Even now, Claude Code has mediocre taste, and auto mode would be pretty bad for our research coding work. (Though it is great for more standard cookie-cutter coding projects.) But it can bang out simple empirical tests well, and test basically what we asked for most of the time.
Other than that, it is still mostly Google Search Plus Plus.
Are Fable/Sol any different in this regard, in your experience? Also paging @David Lorell.
(I’d say there’s no significant difference in my experience, but I’ve gotten really lazy about testing that sort of stuff.)
Even prior to Fable, Claude Code had reached the point of accelerating our coding work dramatically. That was a pretty recent development; prior to the last few months, LLM coding contributions were relatively marginal for the sort of coding problems we work on. Even now, Claude Code has mediocre taste, and auto mode would be pretty bad for our research coding work. (Though it is great for more standard cookie-cutter coding projects.) But it can bang out simple empirical tests well, and test basically what we asked for most of the time.
Other than that, it is still mostly Google Search Plus Plus.
Jury’s still out I’m afraid. Currently stress testing both. Definitely upgrades on the things the previous ones were already good-ish at though.
I’d appreciate an update if you see any unexpected signs of life on the “novel theorywork” side of things.
I made a Manifold market about this: