Thread

1. wasting_time · 1790884160 · focus · HN ↗

   So, how are people actually using Pi? Here I am with Claude Code and Codex in a terminal like a caveman.

   1. darklinear · 1790892778 · focus · HN ↗

      I use pi with a ChatGPT subscription. I find that it does better than the native codex harness: - it's very token efficient. I've had whole profiling + refactoring sessions finish in <20k tokens, whereas in codex you can get close to that with just all the cruft OpenAI loads by default before you even send your own messages - the token efficiency means turns are a lot snappier - fine-grained context control by default - I have to disable a bunch of stuff in codex so it doesn't pollute my context with generated memories - I find that OpenAI model sometimes struggle to navigate codex' sandboxing, and burn a bunch of tool calls retrying outside the sandbox when the sandboxed command fails

      1. culopatin · 1790914785 · focus · HN ↗

         I gave up on these things thinking that you always needed an API. How does it work with subscriptions?

         1. coopykins · 1790923060 · focus · HN ↗

            Codex generally lets you use the subscription with 3rd party agents / harnesses. ON the PI 1.0 you can directly use the openAI log in to hook up your account, so it should be pretty straight forward. I haven't tried myself yet.
         2. kccqzy · 1790957121 · focus · HN ↗

            Claude subscriptions require usage credits IIRC. OpenAI is more generous and allows the use of the actual subscription.

Unofficial Hacker News client; not affiliated with Y Combinator.