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 threadsunaurus1d ago

Has anybody else noticed a pretty significant shift in sentiment when discussing Claude/Codex with other engineers since even just a few months ago? Specifically because of the secret/hidden nature of these changes.

I keep getting the sense that people feel like they have no idea if they are getting the product that they originally paid for, or something much weaker, and this sentiment seems to be constantly spreading. Like when I hear Anthropic mentioned in the past few weeks, it's almost always in some negative context.

Show threadjakobnissen1d ago
Yeah I’ve seen this too. It’s difficult for me to tell if the complaints are due to a legitimate undisclosed nerf of Claude, or whether it’s just the initial awe of Opus 4.6 fading and people increasingly noticing its mistakes.
Show threadkingkongjaffa

Just one more anecdote:

I'm on the enterprise team plan so a decent amount of usage.

In March I could use Opus all day and it was getting great results.

Since the last week of March and into April, I've had sessions where I maxed out session usage under 2 hours and it got stuck in overthinking loops, multiple turns of realising the same thing, dozens of paragraphs of "But wait, actually I need to do x" with slight variations of the same realisation.

This is not the 'thinking effort' setting in claude code, I noticed this happening across multiple sessions with the same thinking effort settings, there was clearly some underlying change that was not published that made the model get stuck in thinking loops more for longer and more often without any escape hatch to stop and prompt the user for additional steering if it gets stuck.

Apr 12 at 9:31amWeb
Show threadUqWBcuFx6NV4r23h ago
Whenever I see Opus say “but wait, …”—which is all the time—I get a little bit closer toward throwing my computer out the window. Sometimes I just collapse the thinking section, cross my fingers, and wait for the answer. It’s too frustrating watching the thinking process.
Show threadadahn23h ago

I’ve seen the point raised elsewhere that this could be the double usage promo that was available from the 13th of March to the 28th. ie. people getting used to the promo then feeling impacted when it finished.

Although it seems that enterprise wasn’t included, so maybe not in your case.

https://support.claude.com/en/articles/14063676-claude-march...

Claude March 2026 usage promotion | Claude Help Center

Show threadcyanydeez23h ago
its sounds like, tinfoil hat, they reduced the quant size of their model and tried to mask the change with the promo. your theory only addresses the spend not the reduced realiability
Show threadderangedHorse22h ago
[dead]
Show threadderangedHorse22h ago

It's probably because you didn't specify "make no mistakes" /s

In all seriousness though, I've observed the same thing with my own usage.