maroziza

Shifted to K3 and it is like a fresh air. While Fable and Sol very good at _generating_ code i even cannot force sol to just read all relevant source files. As result it reinvent existing things or assumes too much about internals of other, which lead to incorrect uses. Even with hard planing mode GPT burned 33% of week tokens for 3 hours producing no result and even cannot find root cause, but K3 fixed it in a minutes. Hilarious that while software not started with empty cache Sol handcrafted empty cache to let it start. Having full procedure right in the MEMORY.md. K3 found this, and downloaded cache correctly. But while using gen5 models i always feeling myself ignored. Any commands, steering anything - just ignoring. At first i added lots of hooks, no "?", expect in rust code, bash hook ban for find|grep|tail, with notice to use ltsp but then it started to ignore strategically. Also whole "thinking" thing is hidden from claude. regenerated thinking summary is incomplete and not useful. While being very verbose kimi k3 doing good job providing whole train of thoughts. So looks like claude degradation started from 4.6 comes to a logical end. Maybe i missing something and changing existing code beyond bug fixes is not a way to go. But there is no currently stable way to generate code on hier of specs and lean models i'd like to.

The main reason is scale and support, here in ukraine we bought all 21k pickups in europe, it is very hard to sustain tham at same time, so if you have any enterprise you'd want a park of SAME vehicle, so for single buy - yes, it will your beloved hilux for rest of your long life. but if you want 100 pickups, 1000? and parts are scarse now. and than you can even customize them. but even in retail you will have extra support and guarantee for new pickup. Steering rack is just unabtainium here, so there will be every other part for 20 year SUV/Pickup soon.