[thevinter]

Pi was probably the best ad for Claude Code I ever saw.

After my max sub expired I decided to try Kimi on a more open harness, and it ended up being one of the worst (and eye opening experiences) I had with the agentic world so far.

It was completely alienating and so much 'not for me', that afterwards I went back and immediately renewed my claude sub.

https://www.thevinter.com/blog/bad-vibes-from-pi

[mccoyb]

> I would say that the project actively expects you to be downloading them to fill any missing gaps you might have.

Where did you get this perspective from?

> I thought pi and its tools were supposed to be minimal and extensible. So why is a subagent extension bundling six agents I never asked for that I can’t disable or remove?

Why do you think a random subagents extension is under the same philosophy as pi?

Your blog post says little about pi proper, it's essentially concerned with issues you had with the ecosystem of extensions, often made by random people who either do or do not get the philosophy? Why would that be up to pi to enforce?

[the_mitsuhiko]

Sharing extensions is very much the philosophy. Using them however is less so.

Pi ships with docs that include extensions and the agent looks there for inspiration if you ask it to build a custom extension.

Looking at what others publish is useful!

[CGamesPlay]

> if I start the agent in ./folder then anything outside of ./folder should be off limits unless I explicitly allow it, and the same goes for bash where everything not on an allowlist should be blocked by default.

Here's the problem with Claude Code: it acts like it's got security, but it's the equivalent of a "do not walk on grass" sign. There's no technical restrictions at play, and the agent can (maliciously or accidentally) bypass the "restrictions".

That's why Pi doesn't have restrictions by default. The logic is: no matter what agent you are using, you should be using it in a real sandbox (container, VM, whatever).

[esafak]

But the agent has to interact with the world; fetch docs, push code, fetch comments, etc. You can't sandbox everything. So you push that configuration to your sandbox, which is a worse UX that the harness just asking you at the right time what you'd like to do.

[the_mitsuhiko]

I too would like to know what a good UX looks like here but I have doubts that the permission prompts of Claude are the way to go right now.

Within days people become used to just hitting accept and allowlisting pretty much everything. The agents write length scripts into shell scripts or test runners that themselves can be destructive but they immediately allowlisted.

[CGamesPlay]

Well, you are imagining a worse UX, but it doesn't have to be. Pi doesn't include a sandboxing story at all (Claude provides an advisory but not mandatory one), but the sandbox doesn't have to be a simple static list of allowed domains/files. It's totally valid to make the "push code" tool in the sandbox send a trigger to code running outside of the sandbox, which then surfaces an interactive prompt to you as a user. That would give you the interactivity you want and be secure against accidentally or deliberately bypassing the sandbox.

[esafak]

So you have to set up that integration instead of letting the agent do it. I suppose the sandbox is more configurable, but do you need that? I thought the draw of pi was that you didn't do all that and let it fly, wheeee!

edit: You're not making it sound easy at all. I don't have to build anything with the other agents.

[CGamesPlay]

Certainly not. Pi is "minimalist", so the draw is that it's "easy" to set it up yourself. You can not do that and run it in yolo mode, and you can do that with Claude Code too. Heck you can even use this hypothetical real-sandbox-with-interactive-prompts with Claude Code instead, once you build it.

Back to my original point: Claude Code gives you a false feeling of security, Pi gives you the accurate feeling of not having security.

[tern]

I had a very similar experience. I have different preferences, but ultimately, my takeaway was that if I want to follow my own version of their philosophy, I should just create my own thing.

In the meantime, the codex/cc defaults are better for me.

[rcarmo]

Paraphrasing The Dude, that’s like, just your opinion, man.

[a96]

> As it turns out, the opinions in question are that bash should be enabled by default with no restrictions, that the agent should have access to every file on your machine from the start, and that npm is the only package manager worth supporting.

Yep. This is why I've been going "Hell, no!" and will probably keep doing so.

[raincole]

Technically you're not allowed to use Claude subscription account with Pi (according to Anthropic's policy). So yeah, Pi is the best anti-ad against Anthropic.

[NamlchakKhandro]

hypegrift