lsdmtme1d ago

Anthropic silently downgraded cache TTL from 1h → 5M on March 6th

https://github.com/anthropics/claude-code/issues/46829

Cache TTL silently regressed from 1h to 5m around early March 2026, causing quota and cost inflation · Issue #46829 · anthropics/claude-code

Cache TTL appears to have silently regressed from 1h to 5m around early March 2026, causing significant quota and cost inflation Summary Analysis of raw Claude Code session JSONL files spanning Jan...

GitHub
Show threaddavidkuennen
On slightly off topic note: Codex is absolutely fantastic right now. I'm constantly in awe since switching from Claude a week ago.
Apr 12 at 8:59amWeb
Show threadlifty1d ago
I made this switch months ago, ChatGPT 5.4 being a smarter model, but I’ve had subjective feelings of degradation even on 5.4 lately. There’s a lot of growth in usage right now so not sure what kind of optimizations their doing at both companies
Show threadvidarh1d ago
Codex has been good quality wise, but I hit limits on the Codex team subscription so quickly it's almost more hassle that it is worth.
Show threadtoenail1d ago
I have also switched from claude to codex a few weeks ago. After deciding to let agents only do focused work I needed less context, and the work was easier to review. Then I realized codex can deliver the same quality, and it's paid through my subscription instead of per token.
Show threadonion2k1d ago
I use Codex at home and Opus at work. They're both brilliant.
Show threadyukIttEft1d ago

I'm currently "working" on a toy 3d Vulkan Physx thingy. It has a simple raycast vehicle and I'm trying to replace it with the PhysX5 built in one (https://nvidia-omniverse.github.io/PhysX/physx/5.6.1/docs/Ve...)

I point it to example snippets and webdocumentation but the code it gens won't work at all, not even close

Opus4.6 is a tiny bit less wrong than Codex 5.4 xhigh, but still pretty useless.

So, after reading all the success stories here and everywhere, I'm wondering if I'm holding it wrong or if it just can't solve everything yet.

Vehicles — PhysX SDK Documentation

Show threadlukan1d ago

" or if it just can't solve everything yet."

Obviously it cannot. But if you give the AI enough hints, clear spec, clear documentation and remove all distracting information, it can solve most problems.

Show threadseba_dos11d ago
It works somewhat well with trivial things. That's where most of these success stories are coming from.