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

331–340 of 447 posts

Re: Anthropic downgraded cache TTL on March 6th

#331

Post by greycol »

stri8ted wrote: post #261
MattRix wrote: post #200

Earlier quoted context omitted.

This is close, but the real problem isn’t that the food is underpriced, it’s that the supply of ingredients is severely limited.

Those are the same thing

They are not if there aren't customers who are willing to pay more. For instance imagine a widget that lasts 1 year and is just under 1/2 the price of one that lasts 2 years. There may be high demand because it's the more economical option. If you raise the price so that it's 1/2 the price of the 2 year widget then demand collapses without effecting supply.

Re: Anthropic downgraded cache TTL on March 6th

#333

Post by NewsaHackO »

bearjaws wrote: post #263
bustah wrote: post #239

[flagged]

Then throw in the people using $10k in their token burning "gastown" and bragging on Twitter... I haven't really hit real usage limits in the past 2 weeks, and part of me wonders if its a loud minority who all abused Claude Code, and now Anthropic has just permanently gimped their accounts. Something like if you are in the top 5% of users, they are now giving you limits to bring you down to the average user.

I think this is clearly it, also a lot of people using Openclaw have realized that no one agrees with them that they deserve to use the sub pricing for their third-party service and have to use the API, so they post a bunch of vindictive stuff about Anthropic to "get back" at them. This exact same thing happened with Gemini, when they started lying about Google personal accounts getting banned to attempt to spite them.

Re: Anthropic downgraded cache TTL on March 6th

#334

Post by themafia »

disillusioned wrote: post #8

It's also routinely failing the car wash question across all models now, which wasn't the case a month ago. :-/ Seeing some things about how the effort selector isn't working as intended necessarily and the model is regressing in other ways: over-emphasizing how "difficult" a problem is to solve and choosing to avoid it because of the "time" it would take, but quoted in human effort, or suggesting the "easier" path f…

Step 1: Sell at a loss.

Step 2: Panic.

Step 3: Destroy product.

Re: Anthropic downgraded cache TTL on March 6th

#335

Post by TheTaytay »

benced wrote: post #221

Anthropic responded: https://github.com/anthropics/claude-code/issues/46829#issue...

This should be the top comment. The OP misunderstands the change and has their LLM write an expose. The company responds with a well-reasoned explanation that it would actually cost MORE money if there was a global 1h default for ALL prompts. It gets downvoted and the pitchforks stay out because…I presume the words like “cache read likelihood” sounds like made up fluff to the audience, rather than an actual explanation?

Re: Anthropic downgraded cache TTL on March 6th

#336

Post by cindyllm »

themafia wrote: post #334
disillusioned wrote: post #8

It's also routinely failing the car wash question across all models now, which wasn't the case a month ago. :-/ Seeing some things about how the effort selector isn't working as intended necessarily and the model is regressing in other ways: over-emphasizing how "difficult" a problem is to solve and choosing to avoid it because of the "time" it would take, but quoted in human effort, or suggesting the "easier" path f…

Step 1: Sell at a loss. Step 2: Panic. Step 3: Destroy product.

[dead]

Re: Anthropic downgraded cache TTL on March 6th

#337

Post by killingtime74 »

jazzyjackson wrote: post #326
oorza wrote: post #293

Earlier quoted context omitted.

Are we at the point where there are external constraints that cash can't solve?

can't tell if you're being facetious but yes, there's not enough cash in the world to double energy/silicon fab capacity in a year. Infrastructure takes time, hardware is hard, and you have to be willing to bet that the demand will be there 5 years from now to make an investment today.

Until one has the entire supply of world GPU production, cash can solve it by out bidding others

Re: Anthropic downgraded cache TTL on March 6th

#338

Post by wahnfrieden »

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…

Instead of "pointing it" at docs, you need to paste the docs into context. Otherwise it will skim small parts by searching. Of course if you're using an obscure tool you need to supply more context.

Xhigh can also perform worse than High - more frequent compaction, and "overthinking".

Re: Anthropic downgraded cache TTL on March 6th

#339

Post by philpem »

pbowyer wrote: post #268
aerhardt wrote: post #231

Earlier quoted context omitted.

How do people like that ascend to CTO?

The Peter Principle: https://en.wikipedia.org/wiki/Peter_principle

Or more cynically they reach their level of competence, go one level further and stay there to keep them from ruining the productivity of the people doing the work...

Re: Anthropic downgraded cache TTL on March 6th

#340

Post by aftbit »

andai wrote: post #65
sunaurus wrote: post #16

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 spreadin…

Well, off the top of my head: - Banning OpenClaw users (within their rights, of course, but bad optics) - Banning 3rd party harnesses in general (ditto) (claude -p still works on the sub but I get the feeling like if I actually use it, I'll get my Anthropic acct. nuked. Would be great to get some clarity on this. If I invoke it from my Telegram bot, is that an unauthorized 3rd party harness?) - Lowering reasoning eff…

Huh I've noticed that! Opus hallucinates answers and provides contradictory reasoning to me much more regularly during the past couple of weeks than it did in February.

For example, after a question about a script that used taskset and CUDA_VISIBLE_DEVICES to handle NUMA domains on a parallel GLUE evaluation run:

>Round 2 tasks reuse GPU slots that Round 1 may still be occupying. Cola, SST-2, and QQP are small datasets and will likely finish before MNLI, but QNLI is sizable. If QNLI (GPU 3, slot 3) is still running when Round 2 launches, that's fine — they're on different slots. But more importantly, Round 2 uses slots 5/6/7 (GPUs 7/0/1), while Round 1 uses slots 0/1/2/3/4 (GPUs 4/5/2/3/6). So there's no GPU collision — you're good here actually. Disregard, this is clean.

Post reply on HN