←back to thread

A Research Preview of Codex

(openai.com)
383 points meetpateltech | 6 comments | 16 May 25 15:02 UTC | HN request time: 0.206s | source | bottom
Show context
tptacek ◴[16 May 25 15:30 UTC] No.44006672[source]▶
Maddening: "codex" is also the name of their open-source Claude-Code-alike, and was previously the name of an at-the-time frontier coding model. It's like they name things just to fuck with us.
replies(4): >>44006709 #>>44007079 #>>44007281 #>>44007680 #
1. tekacs ◴[16 May 25 15:35 UTC] No.44006709[source]▶
So -- that client-side thing is _technically_ called `codex-cli` (in the parent 'codex' repo, which looks like a monorepo?).

Still super confusing, though!

I feel like companies working with and shipping LLMs would do well to remember that it's not just humans who get confused by this, but LLMs themselves... it makes for a painful time, sending off a request and noting that a third of the way into its reasoning that the model has gotten tow things with almost-identical names confused.

replies(2): >>44006812 #>>44007245 #
2. tough ◴[16 May 25 15:44 UTC] No.44006812[source]▶
they also have a dual implementation on rust and typescript there's codex-rs in that monorepo
replies(1): >>44007417 #
3. quantadev ◴[16 May 25 16:21 UTC] No.44007245[source]▶
If it's name is 'codex-cli' then that means "Codex Command Line Interface" so the name is absolutely codex.
4. fabmilo ◴[16 May 25 16:38 UTC] No.44007417[source]▶
more excited about the rust impl than the typescript one.
replies(1): >>44007642 #
5. tptacek ◴[16 May 25 17:00 UTC] No.44007642{3}[source]▶
Besides packaging of their releases, what possible difference could that make in this problem domain?
replies(1): >>44008172 #
6. tough ◴[16 May 25 17:56 UTC] No.44008172{4}[source]▶
I just think it's nice to have open source code to reference so maybe he meant just in that -educational- way, certainly more to learn from the rust one than the TS one for most folks? even if the problem-space doesn't require system-level safety code indeed