Its "pure capabilities" are definitely worse than Fable, but I find codex has a much more pleasant style and is in comparison much more generous with its limits.

▲

dmix 14 hours ago | parent | next [-]

Codex (+Sol) feels a lot more human for sure. Fable 5 is so, so wordy.

▲

TuxSH 14 hours ago | parent | prev | next [-]

It used to be true up to 2w ago, but with the new/reinstated 5h limits I wouldn't be so sure anymore...

	▲	selectodude 13 hours ago \| parent \| next [-]
		that's news to me, I'm still getting weekly limits, no hourly limits.
	▲	panos_news 14 hours ago \| parent \| prev [-]
		Claude has a better 5hr limit?

▲

versteegen 14 hours ago | parent | prev [-]

Ugh, people are still saying the Codex limits are more generous. They're not, Claude's are over 2x higher, have been for months! [1] It's just that Claude uses far more tokens, 2-3x is common. Except sometimes GPT will use just as many or even go into a compact loop and then your quota is gone, little headroom for hard tasks.

[1] https://devforth.io/agents-for-code/?sortby=monthly-value And I can confirm the numbers, I subscribe to both and watch the numbers

	▲	seaurchinzee 13 hours ago \| parent \| next [-]
		That website seems to suggest that Opus 5 spends ~57 cents per task, while GPT 5.6 Sol spends ~49 cents per task? That ratio doesn't feel quite right to me. Artificial Analysis says Opus 5 High costs nearly ~3x as much as GPT 5.6 Sol High for a given task: https://artificialanalysis.ai/models/comparisons/claude-opus...
	▲	isoprophlex 14 hours ago \| parent \| prev \| next [-]
		No no our coffee is not more expensive! The serving sizes are just smaller!
	▲	trentor 14 hours ago \| parent \| prev \| next [-]
		I don't get it. It's the same result.
	▲	import 14 hours ago \| parent \| prev \| next [-]
		Well at the end of the day, I can finish more work with the codex limits.
	▲	re-thc 13 hours ago \| parent \| prev [-]
		> people are still saying the Codex limits are more generous. They're not They are if you follow Tibo on the resets.