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

Re:Anthropic silently downgraded cache TTL from 1h → 5M on M... by foofloobar on Sunday April 12, 2026 @03:43PM (#47743612)

Claude Code and the subscription are now less useful than a few months ago. Claude Code and the service seem to pick up more and more issues as time goes by: more bugs, fast quota drain, reduced quota, poor model performance, cache invalidation problems, MCP related bugs, potential model quantization and other problems.

Claude Code was able to implement something in one shot. It was decent for a proof of concept initial implementation. It's barely able to do work now with full specs and detailed plans.

ChatGPT is also being watered down.

It seems obvious that Anthropic and OpenAI aren't the solution to any problem.

[ Parent | on HN ]

Re:Anthropic silently downgraded cache TTL from 1h → 5M on M... by trollbridge on Sunday April 12, 2026 @03:47PM (#47743659)

I caught up with a friend who said he's really happy with Cursor (currently using the multi-model option where it composes, and reserving use of Opus 4.6 for only when he actually needs the extra power).

Quite interesting considering all the claims that Cursor was dead a few months ago.

[ Parent | on HN ]

Re:Anthropic silently downgraded cache TTL from 1h → 5M on M... by foofloobar on Sunday April 12, 2026 @03:54PM (#47743743)

I wouldn't trust another company either. Some people have reported some issues with Cursor. The solution is probably not a cloud API with unknown quotas or pay as you go pricing.

[ Parent | on HN ]

Re:Anthropic silently downgraded cache TTL from 1h → 5M on M... by trollbridge on Monday April 13, 2026 @11:32AM (#47753491)

An advantage with Cursor, though, is you're paying for your own tokens since Cursor doesn't run their own foundational models. So the incentives are more closely aligned with the customer.

[ Parent | on HN ]

Re:Anthropic silently downgraded cache TTL from 1h → 5M on M... by ecocentrik on Sunday April 12, 2026 @03:56PM (#47743768)

They are clearly straining under new demand and everyone is being served highly quantized models without notice.

[ Parent | on HN ]

Re:Anthropic silently downgraded cache TTL from 1h → 5M on M... by throw_m239339 on Sunday April 12, 2026 @06:00PM (#47745016)

Every single one of these AI services are running at loss, they are subsidized. Anybody who is surprised that these services are going to get degraded and their cost go up substantially learned nothing from the last 20 years of SAAS. It never gets cheaper.

[ Parent | on HN ]

Re:Anthropic silently downgraded cache TTL from 1h → 5M on M... by vbezhenar on Sunday April 12, 2026 @10:12PM (#47746747)

Use cloud AI hoster with open model. Can't get more transparent and reliable than that. They won't subsidize anything, because the whole point of their business is to rent hardware. Open models won't go anywhere, they're there to stay.

The quality will be a bit behind frontier proprietary models. You gotta pay for what you use, no way to cover your expenses from peers underusing their subscription. But otherwise it should be a reasonable middle ground, with very little risk of rug being pulled out from you.

[ Parent | on HN ]