codex gtp-5.5 is far superior to opus 4.7 working on large projects

the__alchemist 10 minutes ago | parent | next [-]

You're using last week's model; Opus 4.7 is old news. Opus 6.9 is the new hotness; it is a better product manager than GPT, and has more X productivity. It replaced our junior dev team, and tells me my hair looks good.

▲

meowface 20 minutes ago | parent | prev | next [-]

GPT-5.5 is the better programmer but Opus 4.8 remains the better system architect and product designer.

Codex is very "miss the forest for the trees", but is much better at successfully making large changes in large codebases. Claude Code makes more mistakes, but has more taste and a better grasp on idiomatic and elegant software development.

If you can afford to, I recommend juggling both.

▲

theturtletalks 10 minutes ago | parent | next [-]

Great analysis and follows my experience as well. Codex is better when you know how you want the design and the architecture and you drive the agent a lot more aggressively. Claude Code feels like more autopilot so executives and users who didn’t code before AI like it a lot more.

But I feel like an expert who can drive GPT aggressively will out perform Opus. It’s why some smart people I know are opting for GPT and have fallen off on Opus. It’s like asking an F1 driver to sit in a taxi.

▲

bayindirh 14 minutes ago | parent | prev [-]

I find arguing that a complex weighted graph has a taste is interesting.

This is not a jab, but a genuine curiosity of mine.

	▲	knollimar 5 minutes ago \| parent \| next [-]
		The roulette pockets for the model are bigger for some outputs than others. Draw a big enough black box around it and a different one around humans and it's insistinguishable.
	▲	alstonite 9 minutes ago \| parent \| prev [-]
		The taste that the complex weighted graph was trained on was better for one than the other I think is the long winded way to say it

▲

RA_Fisher 18 minutes ago | parent | prev | next [-]

In what ways? LM Arena has Opus 4.7 w/ 1567 -/+ 7 vs. 1505 -/+ 10 from GPT-5.5 Codex in code. I'm currently using both.

Admittedly my recent experience tilts Opus now 4.8, but you and others have my interest piqued re: GPT-5.5 Codex so I'm trying that more now.

▲

BoredPositron 24 minutes ago | parent | prev | next [-]

Not everyone is a developer...

	▲	keyle 5 minutes ago \| parent \| next [-]
		Soon none of us will be! right?
	▲	_puk 23 minutes ago \| parent \| prev [-]
		And 4.7 is so last week..

▲

oofbey 13 minutes ago | parent | prev | next [-]

GPT 5.5 still invents facts rather than looking them up, and manages to come across both as condescending and sycophantic. It feels like talking to a used car salesman.

▲

dangus 15 minutes ago | parent | prev [-]

Opus 4.7 is not the current version of Opus.