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.

- https://github.com/MLFlexer/smart_workspace_switcher.wezterm

- https://github.com/MLFlexer/resurrect.wezterm

However is some cases when it could be little more tricky, for instance I'm using LSP for Scala (https://scalameta.org/metals/) which on start trying to automatically detect JDK version for project from environment. So if my project depends on JDK 11 it might required for me manually start LSP from nix-shell to force it use right JVM version.

With Rust is in someway similar, I need to bring some shell with 'rust up' setup so it could install everything for rust-analyzer then emacs can use it.

Regardless emacs itself is few options to manage emacs packages in nix way but for me it not really gives anything so I just use it as on any other OS.