[theturtletalks]

This is exactly why Pi will win. It lets you hot swap models when one is struggling or straight up refusing the task. And since it works with any sub outside Claude Code, you can use it to try different models on OpenCode Go sub or even OpenRouter.

As far as subagent prompts and results being obfuscated, I just let Pi spawn new agents. Using skills and extensions, I’ve essentially built a software factory using Pi and a custom terminal multiplexer.

It’s a shame apps like T3 Code and other UI for terminal apps don’t support Pi and I’m glad to use the terminal above those that lock me in further.

[rahimnathwani]

"I’ve essentially built a software factory using Pi and a custom terminal multiplexer."

I'm curious to know more about this. I was thinking about doing something similar using tmux (i.e. have one coding agent open up new ones in tmux and use 'send-keys' to control them). Is there any reason I might want to consider a different path? Something built on libghostty?

[theturtletalks]

I tried the tmux send-keys but the reading the terminal part was the tough part. Instead of reading terminal output, the Pi extension I made lets Pi read and parse the JSONL files for the session. It also has workspaces with their own memory. I’m about to open-source it, here’s the landing page and docs if you’re interested.

https://vibeghost.org

[rahimnathwani]

How will Pi help? If I'm using pi with my ChatGPT subscription, that won't unlock access to full, unencrypted reasoning traces. If I switch a pi conversation from 5.6-sol to kimi k3, the 5.6-sol reasoning traces won't be visible to kimi k3. I think that's the main point of the article, no?

[theturtletalks]

They mentioned a few things

1. Sessions are locked into Codex and Claude Code so you can’t take a session with you. Pi solves that since they all stay Pi sessions and you can change models in the same session

2. Subagent prompts are not shown. Pi solves this by not supporting subagents out of the box. You can use a number of subagent extensions or build your own which will not be encrypted or hidden.

3. Thinking is hidden and obfuscated. Pi can’t solve this since this is server-side. Though the Codex app is closed source and they could hide more things in that harness. Pi shows you as much as it can from the API. You can also run another model to “decipher” the thinking which you can’t in Codex.

[rahimnathwani]

I see your point. I was thinking mainly about #3 and how nothing, not even pi, can solve that when the reasoning traces are encrypted by the model provider.

[theturtletalks]

I’ve heard of people using DeepSeek to reverse engineer those thinking tokens. Even though they don’t tell you the thinking content, they do tell you how many tokens were used. You can ask DeepSeek how we got from A + x thinking tokens = B.

Claude and Codex flag this as a distillation attempt so you have to use an open weight model and the results are, of course, just a guess.

[apitman]

I'm sure you were referring to the desktop app but codex CLI is open source

[rad-b]

How did you decide on Pi over Opencode? What you see as the “edge” Pi has?

[theturtletalks]

The extension catalog[0] for Pi is really nice and I feel like Pi's TUI is a bit lighter than OpenCode's. I use my custom terminal multiplexer on my phone using Tailscale so the lighter TUI is much better on mobile.

I haven't used OpenCode in months so this might've changed. I'm also thinking of giving JCode a spin since it's even lighter but doesn't have extensions.

0. https://pi.dev/packages

1. https://github.com/1jehuang/jcode

[alasano]

Pi to me felt like when you install a fresh OS with nothing on it and then customize it to your liking.

Sure there are some features that you'll want immediately but when I took at look at the number of slash commands that ship with Claude code I find it ridiculous.

[CuriouslyC]

Pi is more minimal and it can be used to create fancier custom agents for various tasks with plugins. OpenCode is nice if you are only coding though, then the difference isn't really that big unless you want an unusual interface/behavior.

[throw1234567891]

Its extension system.

[aktenlage]

Not OP, but it seems to be the one most likely not following the silicon valley playbook (aka the road to enshitification).

[deadbabe]

The other day, I hit 429 errors with Kimi-K3, had to switch to another model. And if I couldn’t just switch models, I’d be screwed. No work done.