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

201–210 of 447 posts

Re: Anthropic downgraded cache TTL on March 6th

#201

Post by MattRix »

wg0 wrote: post #116
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…

Most of the folks are building CRUD apps with AI and that works fine. What you're doing is more specialized and these models are useless there. It's not intelligence. Another NFT/Crypto era is upon us so no you're not holding it wrong.

This is pretty wrong. Anyone who thinks this stuff is similar to NFTs and crypto hasn’t been paying attention.

Re: Anthropic downgraded cache TTL on March 6th

#202

Post by gfody »

kingkongjaffa wrote: post #40
jakobnissen wrote: post #23

Earlier quoted context omitted.

Yeah I’ve seen this too. It’s difficult for me to tell if the complaints are due to a legitimate undisclosed nerf of Claude, or whether it’s just the initial awe of Opus 4.6 fading and people increasingly noticing its mistakes.

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…

this timing matches my experience, enterprise plan, but using opus from vscode - finished a heavy refactor of a large C# codebase mid march, tried to do basically the same thing early april and couldn't

Re: Anthropic downgraded cache TTL on March 6th

#203

Post by collingreen »

breton wrote: post #188
derangedHorse wrote: post #94

Earlier quoted context omitted.

Pretty bad decision on his part. I've been telling other engineers within my company who felt threatened by AI that this would happen. That prices would rise and the marginal cost for changes to big codebases would start to exceed the cost of an engineer's salary. API credits are expensive, especially for huge contexts, and sometimes the model will use $200 in credits trying to solve a problem that could be fixed in…

> the model will use $200 in credits trying to solve a problem that could be fixed in an hour by a good engineer with enough context So the price for fixing the problem is equal. Sounds like a great argument for AI.

Equal sounds like a terrible argument given all the other problems with replacing engineering thought with ai. I don't know where the line is but I expect it's far beyond equal AND there needs to be a level of "this can debug effectively in production" before that makes any sense for a real business case.

Re: Anthropic downgraded cache TTL on March 6th

#204

Post by jitl »

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…

I saw a big hit to Claude’s intelligence w/ the 1M context window model and the change to adaptive reasoning (github issue linked elsewhere in this thread).

I’m pretty much using 90% Codex now, although since Claude is consistently faster at answering quick questions, I still keep it open for that and for code-reviewing codex/human work before commit.

Re: Anthropic downgraded cache TTL on March 6th

#205

Post by alpha_squared »

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…

I'm pretty sure this is an attempt by both companies to shape a reasonable finance story for their eventual IPO. They need to make this look a lot better than a pump and dump (raising on wild valuations then offloading onto public investors).

Re: Anthropic downgraded cache TTL on March 6th

#206

Post by andriy_koval »

Zetaphor wrote: post #99
jhancock wrote: post #42

Earlier quoted context omitted.

What leads you to say China AI is giving up on open weights? I've been using GLM for over 6 months and pretty happy.

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.

> Meanwhile the Minimax team just released a new open weights version of their 229B model yesterday.

its under new license prohibiting any commercial use.

Re: Anthropic downgraded cache TTL on March 6th

#207

Post by MuffinFlavored »

rlpb wrote: post #80
andai wrote: post #65

Earlier quoted context omitted.

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…

> It's all circumstantial but everything points towards "desperately trying to cut costs". I have been wondering if it's more geared at reducing resource usage, given that at the moment there's a known constraint on AI datacenter expansion capability. Perhaps they are struggling to meet demand?

I wish they would just rip the bandaid to stop everybody's entitled whining.

"We're sorry, what we were able to give you for $100/mo before now needs to be $200/mo (or more). We miscalculated/we were too generous/gave too much away for too little. It's a new technology, we are seeing a ton of demand, we are trying to run a business, hope you understand. If you don't want it, don't pay for it."

Re: Anthropic downgraded cache TTL on March 6th

#208

Post by rendaw »

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…

They also screwed up the API token detection and also blocked a bunch of 1st party tool users for ~24h.

Support consisted of AI bots saying you did something stupid, you did something wrong, you were abusing the system, followed by (only when I asked for it explicitly) claiming to file a ticket with a human who will contact you later (and it either didn't happen or their ticket system is /dev/null).

(By the way this is the 2nd time I've been "please hold" gaslit by support LLMs this exact same way, the other being with Square)

Re: Anthropic downgraded cache TTL on March 6th

#209

Post by embedding-shape »

layer8 wrote: post #177
embedding-shape wrote: post #174

Earlier quoted context omitted.

When it comes to agents like codex and CC it seems to come down to how well you can describe what you want to do, and how well you can steer it to create its own harness to troubleshoot/design properly. Once you have that down, I haven't found a lot of things you cannot do.

Breaking down and describing things in sufficient detail can be one way to ensure that the LLM can match it to its implicit knowledge. It still depends on what you’re trying to do in how much detail you have to spell out things to the LLM. It’s almost a tautology that there’s always some level of description that the LLM will be able to take up.

Well, not just breaking down the task at hand, but also how you instruct it to do any work. Just saying "Do X" will give you very different results from "Do X, ensure Y, then verify with Z", regardless of what tasks you're asking it to do.

That's also how you can get the LLM to do stuff outside of the training data in a reasonably good way, by not just including the _what_ in the prompt, but also the _how_.

Re: Anthropic downgraded cache TTL on March 6th

#210

Post by colechristensen »

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…

>“idgaf about risk you coward, waste some time just do it and stop bitching”

The above was a successful prompt to get Claude to stop whining about effort, difficulty, and time.

Unfortunately abusive language well placed is an effective LLM motivator.

Post reply on HN