COO switches from Claude to Codex for coding tasks
A COO has switched from Claude to Codex for daily coding tasks in professional use. The report notes Claude's tendency toward laziness alongside strengths in taste and context. Codex is described as more eager yet still limited in taste and contextual understanding. The commentary projects that Codex will prevail once remaining gaps close.
#237Nathan Benaich@NATHANBENAICHwhat? the claude app is much better than the chatgpt app
claude code mac app is very good, just as codex mac app is good
chatgpt mac app is horrific
agree multimodality at openai is better
but don’t think this is right read on anthropic.
#671Chamath Palihapitiya@CHAMATHAnthropic needs to solve the computer/power problem or they will be the Friendster of the AI era.
I just ran a semi-complicated stock screening prompt on all four major AIs: Grok, Gemini, ChatGPT and Claude.
The first three returned comparable results. Claude refused to do the work.
Not the way to win guys…
#767elie@ELIEBAKOUCH@jxnlco @PrimeIntellect wasn't release at the start of the experiment + codex had no issue getting on a loop (compare to claude for instance)
@sammcallister I will be very psyched! The more great AI in the world the better
sam mcallister@sammcallister@danshipper I will personally welcome you back to Claude soon
#1494Chubby♨️@KIMMONISMUSClaude is lazy, but has taste and context (no talking about 4.7 tho)
Codex is eager, but still lacks some taste and context.
Once Codex gets both, it’s over.
@danshipper I will personally welcome you back to Claude soon
Dan Shipper 📧@danshipperSuccessfully Codex-pilling the world one text at a time