If theres nobody to share with you’re allowed 3 breaths between each pull.

OT: the three x’s. Is that like a clicking sound?

No sry. I only use idf, and use their create vscode files for lsp to work

And tmux + skills for idf.py work including debug. Also repl on console/uart - agents love cli - including this.

Imo mcp > pure skills for tmux

It’s his knee jerk reaction. I won’t put much into this until i see them stop a Chinese bound vessel

Rough estimate from my personal connections only. Some work places where ai is not possible, but all that have made an effort report good code. You need to work with what it is - a word generator that sometimes gives correct results. Make it research and not trust training. Never let it do things on its own, require a plan and reason. Make it evaluate its own work/plan.

Most issues i have stem from models beeing too eager. Restrain them and remove the “i can do this next…”behaviour.

Context is king - so proper mcp and documentation that is agent facing. I use serena as i can get lsp for yaml, markup and keep these docs like that

Dev-ops where compromised.

Where they believe pulling in new releases without vetting into your environment is good practice…?

We dont even patch windows without vetting…. Why do you do that in your dev env???

In my view it’s about quality and not quantity of the AGENTS/CLAUDE.md

My experience is that starting with what i dont want and the what i do works best. «never rely on training for API documentation, use context7» «don’t use ls/find/grep for symbols, use serena»

Not the best examples, but but.

I do apps that work, i do patches that are production quality. Half the cs world does… I do full stack ai debugging of esp32 projects.

It’s a powerful tool, you just need to learn it’s strong and weak points, just like any other tool you use.

US has hard right and far right. There’s no political opposition