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

311–320 of 447 posts

Re: Anthropic downgraded cache TTL on March 6th

#311

Post by 59nadir »

plusplusungood wrote: post #192
Zetaphor wrote: post #102

Earlier quoted context omitted.

Alternatively products like openclaw have an outsized impact on Anthropic's infrastructure for essentially no benefit to them. Especially when you're taking advantage of the $200 plan. OpenAI has never shyed away from burning mountains of cash to try and capture a little more market share. They paid a billion dollars for a vibe coded mess just for the opportunity to associate themselves with the hype.

> Taking advantage of the $200 plan. No, I'm paying $200 a month for a premium product that I expect premium service for. It's the single most expensive IT expense I have. Taking advantage my foot.

Can you imagine paying the actual cost of it, or a subscription cost that at least ballpark matched it? I don't think I have a single friend or acquaintance who realistically would.

Re: Anthropic downgraded cache TTL on March 6th

#312

Post by shdh »

seba_dos1 wrote: post #93
yukIttEft wrote: post #67

Earlier quoted context omitted.

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…

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

Exactly this, the SNR is polluted by this anecdata because someone was able to implement a CRUD backend they couldn’t before

Re: Anthropic downgraded cache TTL on March 6th

#313

Post by foofloobar »

trollbridge wrote: post #307
foofloobar wrote: post #304

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 init…

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.

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.

Re: Anthropic downgraded cache TTL on March 6th

#314

Post by ecocentrik »

foofloobar wrote: post #304

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 init…

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

Re: Anthropic downgraded cache TTL on March 6th

#315

Post by shdh »

layer8 wrote: post #165

From the recent-ish Dwarkesh podcast, Anthropic seems to be wary about buying/building too much compute [0]. That probably means that they have to attempt to minimize compute usage when there is a surge in demand. Following the argument in the podcast, throwing more money after them, as some in this thread are suggesting, won’t solve the issue, at least not in the short term. [0] https://www.dwarkesh.com/i/187852154/…

Likely accurate

This tends to happen during pretraining phase of new models

Happened with 3.x too

Re: Anthropic downgraded cache TTL on March 6th

#316

Post by 59nadir »

aerhardt wrote: post #231
groundzeros2015 wrote: post #145

Earlier quoted context omitted.

I can’t believe how many small to mid size companies are being destroyed by bad decisions like this. A friend’s company fired all EMs and have engineers reporting to product managers. They aren’t allowed to do refactors because the CTO believes the AI doesn’t need organized code.

How do people like that ascend to CTO?

CTO is in many cases a rank more than a role, and given out accordingly. You should never take someone seriously based on their rank alone, much less a CTO.

Re: Anthropic downgraded cache TTL on March 6th

#318

Post by trollbridge »

matheusmoreira wrote: post #249
beering wrote: post #233

Earlier quoted context omitted.

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.

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.

Cursor?

Re: Anthropic downgraded cache TTL on March 6th

#319

Post by tinodb »

visarga wrote: post #235
fluidcruft wrote: post #161

Earlier quoted context omitted.

claude -p not working would be instant unsubscribe downgrade from Max to Pro and further drive my use of codex. I use both but overall have noticed I reach for Claude less than codex lately because claude keeps getting slower and slower (I have not noticed a drop off in quality, but I use it less and less so maybe I'm not in a good position to notice). Generally I find codex and claude make a good team. I'm not a hea…

I might consider switching to codex from claude pro 20x but I need the post tool use, pre file write and post user message hooks. Waiting on codex to deliver. - pre file write -> block editing code files without a task and plan of work - post tool use -> show next open checkbox in the task to the agent, like an instruction pointer - post user message -> log all user messages for periodic review of intent alignment Th…

I use codex through the pi agent. It’s wonderful and easy to create whatever extension or hook you want!

I’d use it with Claude too if they hadn’t banned it…

Post reply on HN