Even is so stupid but looks like in last few years lot of strange metrics like that used more and more.

only partially and both Sway and Hyperland still doesn't has official support yet.

this blog post explaining some issues https://michael.stapelberg.ch/posts/2026-01-04-wayland-sway-...

For now I can deal with that stuff but it looks like more I use wayland more issues I see so not sure that I will able stick with it long term.

oh now I also has flickers with discord app

in most cases it don't unless this game become really legendary which often not the case. So young person easily can spent 10y in attempt to do that but as result non of those games will be remembered in 2y after release.

But in reality that environment helping only to grow in technical aspects of the job ( maybe also learning some market forces) but it leads to severe degradation in artistic practice of which person original desire cultivate even not realizing that just because is no business need for anything like that. Bus sines can be fine by just coping that everyone else doing or implementing some one else vision.

    Thinking mode for general tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

    Thinking mode for precise coding tasks (e.g. WebDev): temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

    Instruct (or non-thinking) mode for general tasks: temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

    Instruct (or non-thinking) mode for reasoning tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

unfortunately it lot of things in AWS that also could be messed up so it might be really hard to research what is going on. For example, you could have hundreds of Lambdas running without any idea where original sources and how they connected to each-other, or complex VPCs network routing where some rules and security groups shared randomly between services so if you do small change it could lead to completely difference service to degrade (like you were hired to help with service X but after you changes some service Y went down and you even not aware that it existed)

that usually very hard to do part, and is was possible to spent few days on something like that in real word before LLMs. But with LLMs is worse because is not enough to have those requirements, some of those won't work for random reasons and is no any 'rules' that can grantee results. It always like 'try that' and 'probably this will work'.

Just recently I was struggled with same prompt produced different result between API calls before I realized that just usage of few more '\"' and few spaces in prompt leaded model to completely different route of logic which produced opposite answers.

I personally not even convinced that Claude Code any better on average than something like Aider+Gemini 3 or other good model. May be in some specific cases it actually better but in those Aider+'Antropic Model via API' most likely will work too.