News for hackers. Stuff that matters.
Re:Elevated errors on claude.ai, Claude Code, and platform.c... by smallerfish on Friday November 13, 2026 @06:37AM (#50482072)
I used claude for the first time in months yesterday (have been using codex, ran out of resets this week). I had picked up from general consensus comments that 5.5 had fixed the opus 5 issues, but that's far from the case. Its "personality" is still smartass, know it all, and whiny. It disregards specifications in tickets if it thinks it knows better. It complains about the size of tasks when it reads task descriptions. I've gotten used to codex, which just jumps in and does stuff (which of course carries its own set of issues). I have no love for Altman, but their product is still better at the moment.
Re:Elevated errors on claude.ai, Claude Code, and platform.c... by alexgoodhart on Friday November 13, 2026 @06:39AM (#50482093)
I mean, yeah I agree. Claude is a condescending experience
Re:Elevated errors on claude.ai, Claude Code, and platform.c... by ramraj07 on Friday November 13, 2026 @06:42AM (#50482117)
The post was about their uptime. How is this relevant.

Even if it vaguely is, why do people think subjective anecdotal thoughts about which model is better are a good discussion topic. If there’s an objective evaluation idea that would be useful.

I run evals for a very specific domain. Opus 5.5 is still the industry leader (we can’t use Fable class yet).

Re:Elevated errors on claude.ai, Claude Code, and platform.c... by smallerfish on Friday November 13, 2026 @06:45AM (#50482147)
> How is this relevant.

It's relevant because there's only so many "yep it's down" comments that are interesting. They have a technology problem which isn't fixed. They're about to go IPO. Their marketing is clearly still working, but subjective experience with both contradicts the marketing.

> I run evals for a very specific domain.

What do your evals test for?

Re:Elevated errors on claude.ai, Claude Code, and platform.c... by greenchair on Friday November 13, 2026 @07:12AM (#50482401)
We come here to share our experiences with tech so yeah it is relevant. His anecdotes are just as valid as yours.