Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Anthropic downgraded cache TTL on March 6th

github.com

Post reply on HN
Print view View original

151–160 of 447 posts

Re: Anthropic downgraded cache TTL on March 6th

#151

Post by layer8 »

apetresc wrote: post #126
andai wrote: post #105

Earlier quoted context omitted.

> over-emphasizing how "difficult" a problem is to solve and choosing to avoid it because of the "time" it would take I heard a while back Claude refused to attempt a task for days, saying it would take weeks of work. Eventually the user convinced it to try, and it one-shotted it in 30 seconds.

For days ? Someone spent days trying to convince Claude to do something?

If you asked yesterday, and asked again today, then you asked for days. OP might be trying to express that it wasn’t just a temporary fluke.

Re: Anthropic downgraded cache TTL on March 6th

#152

Post by hirako2000 »

There is a chef, he opens a restaurant. Delicious food.

It costs him more in ingredients alone than he charges. He even offers some pseudo unlimited buffet, combo sets, and happy hours.

He announced a new restaurant, apparently it will be even better, so good he's a bit worried. He makes sure to share his worries while he picks a few select enterprise for business parties and the likes.

In the meantime he cracks down on free buffet goers who happen to eat too much, and downgrades all ingredients without notice to finally hope to make a profit.

Re: Anthropic downgraded cache TTL on March 6th

#153

Post by layer8 »

yukIttEft wrote: post #67
davidkuennen wrote: post #13

On slightly off topic note: Codex is absolutely fantastic right now. I'm constantly in awe since switching from Claude a week 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…

My impression is that it always comes down to how well what you’re trying to do pattern-matches the training set.

Re: Anthropic downgraded cache TTL on March 6th

#154

Post by Throaway199999 »

dns_snek wrote: post #127
Zetaphor wrote: post #99

Earlier quoted context omitted.

People keep repeating this without any real thought behind it because of the high profile resignations on the Qwen team. Meanwhile the Minimax team just released a new open weights version of their 229B model yesterday. So much for that narrative. The AI landscape in China is larger than just Qwen and Alibaba.

Of course, but for how long? Do you think that companies will keep giving away valuable assets for free forever, or do you think that in the near future there's going to be an open weights model that's so good that people keep using it indefinitely instead of going back to frontier model providers? The first one is just incredibly naive, the second might be true for some people, for some tasks, but it's not going to…

the asset's value is in being released, so yes

Re: Anthropic downgraded cache TTL on March 6th

#155

Post by albert_e »

So a side effect of this is -- even at 1 hour caching -- ...

If you run out of session quota too quickly and need to wait more than an hour to resume your work ... you are paying even more penalty just to resume your work -- a penalty you wouldnt have needed if session quota was not so restrictive in first place, and which in turn causes you to burn through next session quota even faster.

Seems like a vicious cycle that made the UX very poor. I remember Claude Code with Pro became virtually unuseable in middle of March with session quota expiring within first hour or less for me -- which was wildly different experience from early March.

Re: Anthropic downgraded cache TTL on March 6th

#157

Post by DonHopkins »

gib444 wrote: post #41
simianwords wrote: post #32

Earlier quoted context omitted.

[flagged]

New theory of HN: every post on LLMs will attract the "what is wrong with AI? I don't get it [even though I've posted to HN every day for weeks/months on LLM/AI topics]. Please enlighten me" types

[dead]

Re: Anthropic downgraded cache TTL on March 6th

#158

Post by azuanrb »

As a Pro user, even though these issues and bugs are “new,” the downgrade has been noticeable since January. I’ve unsubscribed because the Pro plan is no longer usable for me.

It’s only making the news now because it’s affecting Max users as well ($100/$200 plans). I understand the need for change, but having zero communication about it is just wrong.

Re: Anthropic downgraded cache TTL on March 6th

#159

Post by natpalmer1776 »

UqWBcuFx6NV4r wrote: post #47
kingkongjaffa wrote: post #40

Earlier quoted context omitted.

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 va…

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.

I stop the thinking and manually correct with explicit instructions or direction. I treat my agents like well meaning ivy-league graduate interns. They lack the experience to know what to do sometimes and need a “common sense” direction every now and then.

Re: Anthropic downgraded cache TTL on March 6th

#160

Post by SyneRyder »

ledauphin wrote: post #144
brookst wrote: post #119

Earlier quoted context omitted.

To be clear they weren’t banned from Claude usage, they were required to use the API and API rates rather than Claude Max tokens. Claude code uses a bunch if best practices to maximize cache hit rate. Third party harnesses are hit or miss, so often use a lot more tokens for the same task.

nah this doesn't explain it. most of the users of those third party harnesses care just as much about hitting cache and getting more usage.

I'm watching a conference talk right now from 2 weeks ago: "I Hated Every Coding Agent So I Built My Own - Mario Zechner (Pi)", and in the middle he directly references this.

He demonstrates in the code that OpenCode aggressively trims context, by compacting on every turn, and pruning all tool calls from the context that occurred more than 40,000 tokens ago. Seems like it could be a good strategy to squeeze more out of the context window - but by editing the oldest context, it breaks the prompt cache for the entire conversation. There is effectively no caching happening at all.

https://youtu.be/Dli5slNaJu0

Post reply on HN