News for hackers. Stuff that matters.
Re:Claude Opus 4.5 by edf13 on Monday November 24, 2025 @02:49PM (#46038403)
I’m threw a few hours at Codex the other day and was incredibly disappointed with the outcome…

I’m a heavy Claude code user and similar workloads just didn’t work out well for me on Codex.

One of the areas I think is going to make a big difference to any model soon is speed. We can build error correcting systems into the tools - but the base models need more speed (and obviously with that lower costs)

Re:Claude Opus 4.5 by chrisweekly on Monday November 24, 2025 @03:15PM (#46038677)
Any experience w/ Haiku-4.5? Your "heavy Claude code user" and "speed" comment gave me hope you might have insights. TIA
Re:Claude Opus 4.5 by pertymcpert on Monday November 24, 2025 @04:38PM (#46039675)
Not GP but my experience with Haiku-4.5 has been poor. It certainly doesn't feel like Sonnet 4.0 level performance. It looked at some python test failures and went in a completely wrong direction in trying to address a surface level detail rather than understanding the real cause of the problem. Tested it with Sonnet 4.5 and it did it fine, as an experienced human would.
Re:Claude Opus 4.5 by chrisweekly on Monday November 24, 2025 @10:38PM (#46042112)
Thanks!
Re:Claude Opus 4.5 by senordevnyc on Monday November 24, 2025 @08:26PM (#46041370)
Try composer 1 (cursor’s new model). I plan with sonnet 4.5, and then execute with composer, because it’s just so fast.