> We are making this choice because we cannot be confident that SpaceX will use our technology within our terms of service, based on our experience with Elon Musk's companies violating contracts. I'm surprised how clear they are about this. Related: Can highly recommend Zed as an alternative, it's better than VSCode with the Codex extension as managing multiple chats is much nicer in Zed. Zed: https://zed.dev/. - Source: Hacker News / 3 days ago

I am not talking about GLM models being served through an Anthropic compatible API. I am talking about ZCode, the harness, being unable to delegate to other harnesses, like using Claude Code (or even OpenCode) within their UI, so that an Anthropic subscription can be used, because they don't let you use 3rd party harnesses directly. It's basically what Paseo: https://paseo.sh/ and Kepler... - Source: Hacker News / 18 days ago

With Agent Client Protocol (ACP) you can keep the same UI and switch not models, but entire agents, that means using tools/prompts/compaction/etc that are tailored for the model. Try Zed[1] for GUI and pool[2] for TUI. [1] https://zed.dev/ [2] https://github.com/poolsideai/pool. - Source: Hacker News / 2 months ago

Devcontainers + Claude + Pi [1] Zed https://zed.dev/ [2] Terminal threads https://zed.dev/blog/terminal-threads As sort of byproduct also replaced Alacritty + Zellij (i just don't have the need to use more, 3 weeks of new setup). - Source: Hacker News / 3 months ago

The simplest mainstream options for tools: 1) Claude Desktop which includes Claude Code for Anthropic: https://claude.com/product/claude-code (alternatively the terminal based version; either way get the subscription) 2) Codex for OpenAI: https://developers.openai.com/codex/app (same as above, subscription preferred instead of paying per token) 3) OpenCode for a variety of models: https://opencode.ai/ (they also... - Source: Hacker News / 3 months ago

Interesting, I built https://pyor.review to fix this exact issue, though it uses AI to categorize the files and groups them by complexity to speed up the review process because most AI generated code is noise, especially migration PRs. - Source: Hacker News / 8 days ago

Have you tried https://pyor.review ? It’s not an editor in that sense but a tool optimized for reviewing PRs produced by AI. - Source: Hacker News / 3 days ago

The migration is self was relativley easy to do with AI, a task that would've taken men months, done in a couple weeks. The not so good part about such migrations is that the resulting PR is huge, it does contain some important parts but most of it was noise and prop renames and mechanical changes. The problem is that Github wasn't really helpful with the review proccess, it doesn't provide a good experience for... - Source: Hacker News / 4 days ago

Reviewing the code is that hard part, but what makes it stressful is GitHub’s poor support for a good PR review experience, I ended up building my own solution (https://pyor.review) to make reviewing the code a lot less stressful. - Source: Hacker News / 5 days ago

Have you tried reviewing code on https://pyor.review instead of checking out the code locally? - Source: Hacker News / 6 days ago