Re:Claude Fable 5: mid-tier results on coding tasks
by hirsto on Thursday June 11, 2026 @07:33PM
(#48497871)
This seems insane to me. Aren't long running tasks an anti pattern at the moment? My understanding of literature is that small mistakes in chat history cause a trend away from performance
[ Parent
| on HN ]
Re:Claude Fable 5: mid-tier results on coding tasks
by colechristensen on Thursday June 11, 2026 @07:54PM
(#48498030)
>Aren't long running tasks an anti pattern at the moment?
Longer running tasks require better setups and several ways of pinning the progress to reality. When you have that though things are quite all right.
A good long running task will run inside a framework that it's not trying to modify.