This post obliterated any chance I had to use or condone Zig commercially. If this is how Zig leadership thinks and acts, plus their stance on AI and GitHub, I'm afraid that the language will stay archived as a neat PL research project in my mind.
I suspect some of those that try to downplay the personal attacks are either on the spectrum or just not acting in good faith.
This post obliterated any chance I had to use or condone Zig commercially. If this is how Zig leadership thinks and acts, plus their stance on AI and GitHub, I'm afraid that the language will stay archived as a neat PL research project in my mind. And maybe it's what Andrew wants.
> he trigger was watching deepseek-flash fail on the simplest /review run, every shellCommand and readFile call bouncing back with a raw zod issues blob, the model unable to recover because the error wasn't in a form it could read. by the end deepseek v4 pro was beating opus 4.7 6/10 times on our internal evals.
I think this is why Xiaomi forked OpenCode and created their own agent hardness, to reduce friction between model and harness:
From what I understood, the gist of it is that uses a bunch of skills in a loop to help LLMs solve the tasks better via browser-testing, debugging, visual-testing, etc..
That's what VSCode next edit does too. It gathers context from the surroundings and recent actions to suggest blocks of code.
It often feels magical. But I find agentic plan->review->implement->review workflow to be a net positive in cohesion, documentation and throughput, relatively speaking.
I can speak for Chrome's MCP which I have more experience.
devtools MCP will have access to more deep level fetures such as performance profiling, lighthouse and network requests in details (headers, auth, cookies...).
For example, I had success using chrome devtools mcp to debug frontend performance issues. The LLM captured and analyzed some nice traces and was able to isolate bottlenecks and unnecessary repaints and reflows.