Re:Anthropic silently downgraded cache TTL from 1h → 5M on M...
by babaganoosh89 on Sunday April 12, 2026 @05:47AM
(#47737753)
There's a github issue for this: https://github.com/anthropics/claude-code/issues/42796
Re:Anthropic silently downgraded cache TTL from 1h → 5M on M...
by matheusmoreira on Sunday April 12, 2026 @06:02AM
(#47737879)
Yes, I commented on it and applied all remedies suggested.
https://news.ycombinator.com/item?id=47664442
Configuration and environment variables seem to have improved things somewhat but it still seems to be hit or miss.
Re:Anthropic silently downgraded cache TTL from 1h → 5M on M...
by watt on Sunday April 12, 2026 @03:40PM
(#47743593)
That issue now is closed, probably as "not planned".
Re:Anthropic silently downgraded cache TTL from 1h → 5M on M...
by beering on Sunday April 12, 2026 @01:11PM
(#47742059)
The real question I see nobody asking is how GPT-5.4 beats Opus at a fraction of the price. I doubt it’s only a question of subsidization. My impression from the past is that GPT-5 was around a Sonnet-sized model, and 5-mini was Haiku-sized. At least on my codebase anyways, Codex one-shots tricky things that Opus needs several tries to fully get right.
Re:Anthropic silently downgraded cache TTL from 1h → 5M on M...
by matheusmoreira on Sunday April 12, 2026 @01:53PM
(#47742442)
I wanted to choose Anthropic because they were apparently more ethical compared to OpenAI, but... Yeah.
Right now the only blocker for me is the lack of Linux support.
Re:Anthropic silently downgraded cache TTL from 1h → 5M on M...
by trollbridge on Sunday April 12, 2026 @04:06PM
(#47743876)
Cursor?
Re:Anthropic silently downgraded cache TTL from 1h → 5M on M...
by alphabettsy on Monday April 13, 2026 @01:22AM
(#47747913)
IMO it doesn’t handily beat it.
It’s typically equivalent, sometimes better, sometimes behind. Better at following a well defined plan, less good at concept exploration and planning imo.
At 1m context it’s basically the same price.
Whether it's due to bugs or actual malice, it's not a good look. I genuinely can't tell if it's buggy, if it's been intentionally degraded, if it's placebo or if it's all just an elaborate OpenAI psyop.