I find codex way more usable. It’s not pretentiously verbose like Claude. It’s also responsive - I can see the progress easily and steer the conversation. With Claude, it might take 15 minutes and I would lose patience.

▲

gck1 12 hours ago | parent | next [-]

Both are verbose in their own way, and both - terrible. Claude models love to throw huge blobs of text in architecture planning / interview conversations, but in not a mentally draining language. OpenAI models are more compact, but very dense & formal - they will speak in RFC language for a button that clicks and submits a form.

So claude: 10 paragraphs of prose

codex: 1 paragraph of jargon over jargon.

	▲	cbg0 10 hours ago \| parent [-]
		I've seen this with GPT, and I usually ask it to put together a more easy to understand document for a specific target audience or reading level and it seems to do okay.

▲

lillecarl 13 hours ago | parent | prev [-]

I held out on OpenAI until last month because I despise Sam Altman, but using Codex is a great experience and 5.5 (medium) I'm on 20$ is very capable, follows instructions when it should and confronts me/challenges me when it should.

UX is nicer where the agent is somehow "separated" from execution.