News for hackers. Stuff that matters.
Re:Claude Fable 5.2 and Mythos 5.2 by andriy_koval on Monday November 09, 2026 @03:04PM (#50431140)
LoC doesn't tell full story.

It could be flat web app with frontend -> api -> db later, or some very complicated system with many components and edge cases. Imo, in second case, Opus still have lots of struggle to understand system as a whole.

Re:Claude Fable 5.2 and Mythos 5.2 by dualvariable on Monday November 09, 2026 @03:29PM (#50431567)
I have a rocket trajectory optimizer that creates a large-ish (~1000 variables x ~1000 constraints) NLP and feeds it to an SQP solver inside this codebase. Not just a REST API over a database.

I guess I do have an outstanding hard problem where the SQP solver crawls across a flat-landscape. Opus 5.5 correctly tells me that is the problem, but isn't very useful in solving the problem (it has helped a bit with solver tuning, but it doesn't really know how to fix it). I have a hundred other bugs and refactoring I can do with Opus 5.5, though, where it happily chews through pretty complicated tasks for me with reasonably light hand-holding. Maybe this Saturday I take whatever credits I have left for the week and throw Fable at it and watch them evaporate.

Re:Claude Fable 5.2 and Mythos 5.2 by andriy_koval on Monday November 09, 2026 @03:35PM (#50431666)
Another dimension is:

It looks like you are working on some experimental system which is not critical atm, so you can mess around, create/fix bug, build prototypes and check them, do research of approaches, etc.

Now, imagine you have similarly complex system, but every second of downtime or bug produces lots of damage. In this case, you can't afford low intelligence vibe coding.

The fact that you deal with hundred of bugs, means that your Op5.5 won't work for second case.