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

341–350 of 447 posts

Re: Anthropic downgraded cache TTL on March 6th

#341

Post by jrockway »

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 have read the HN articles and seen the grumbling from coworkers, but I haven't felt it myself. I am not really a one-shotter, though. I kind of think about how I would refactor / write something myself and walk Claude through that, and nitpick it at each step... and the recent changes haven't really bothered me there. Likely due to being new at it.

Sometimes Claude can be a little weird. I was asking it about some settings in Grafana. It gave me an answer that didn't work. I told it that. "Yeah, I didn't really check, I just guessed." Then I said, "please check" and it said "you should read the discussion forums and issue tracker". I said "YOU should read the discussion forms and issue tracker". It consumed 35k tokens and then told me the thing I wanted was a checkbox. It was! I am not sure this saved me time, Claude. I am not experienced enough to say that this is a deal breaker. While this is burned into my mind as an amusing anecdote, it doesn't ruin the service for me.

My coworkers have noticed a degradation and feel vindicated by some of the posts here that I link. A lot of them are using Cursor more now. I have not tried it yet because I kind of like the Claude flow and /effort max + "are you sure?" yield good results. For now. I'm always happy to switch if something is clearly better.

Re: Anthropic downgraded cache TTL on March 6th

#342

Post by lobf »

travoc wrote: post #305
jrpear wrote: post #243

Earlier quoted context omitted.

Even if you take it as true that prices have risen recently, and may continue to rise as the VC subsidies dry up, they will fall again long-term. Inference will get more power efficient with model-on-chip solutions like Taalas and God willing we will get cheaper and cheaper renewable energy. Despite this I don't think engineers should feel threatened. As long as there is a need for a human in the loop, as today, ther…

Increased demand will not drive down energy costs.

Why not?

Re: Anthropic downgraded cache TTL on March 6th

#343

Post by giancarlostoro »

jrockway wrote: post #341
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 have read the HN articles and seen the grumbling from coworkers, but I haven't felt it myself. I am not really a one-shotter, though. I kind of think about how I would refactor / write something myself and walk Claude through that, and nitpick it at each step... and the recent changes haven't really bothered me there. Likely due to being new at it. Sometimes Claude can be a little weird. I was asking it about some…

How exactly do you use Claude Code, in the browser? Claude Code? The Desktop App (which has a "Code" tab) or some other way? I feel like people who have issues with Claude / Anthropic are not conveying where they are struggling. I see people say they tried "Claude" and didn't like it, but the secret sauce is Claude Code. Claude Code is what most people enjoy using, even if we all wish they would open up the harness, because there's so many more improvements that could go into it.

Re: Anthropic downgraded cache TTL on March 6th

#344

Post by giancarlostoro »

zazibar wrote: post #74
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…

A month ago the company I work at with over 400 engineers decided to cancel all IDE subscriptions (Visual Studio, JetBrains, Windsurf, etc.) and move everyone over to Claude Code as a "cost-saving measure" (along with firing a bunch of test engineers). There was no migration plan - the EVP of Technology just gave a demo showing 2 greenfield projects he'd built with Claude Opus over a weekend and told everyone to copy…

Should have started slowly instead of being so aggressive with it.

Re: Anthropic downgraded cache TTL on March 6th

#345

Post by jrockway »

giancarlostoro wrote: post #343
jrockway wrote: post #341

Earlier quoted context omitted.

I have read the HN articles and seen the grumbling from coworkers, but I haven't felt it myself. I am not really a one-shotter, though. I kind of think about how I would refactor / write something myself and walk Claude through that, and nitpick it at each step... and the recent changes haven't really bothered me there. Likely due to being new at it. Sometimes Claude can be a little weird. I was asking it about some…

How exactly do you use Claude Code, in the browser? Claude Code? The Desktop App (which has a "Code" tab) or some other way? I feel like people who have issues with Claude / Anthropic are not conveying where they are struggling. I see people say they tried "Claude" and didn't like it, but the secret sauce is Claude Code. Claude Code is what most people enjoy using, even if we all wish they would open up the harness,…

Yeah, sorry. Claude Code in my case.

I do use the browser version on occasion. I have no strong feelings one way or the other there. I like it better than Google search in many cases, but probably just search more often.

Re: Anthropic downgraded cache TTL on March 6th

#346

Post by eaf7e281 »

throwaway2027 wrote: post #163
eaf7e281 wrote: post #150

I think they changed the quantification to save computer power for their new model. This might be why the benchmark scores look good, but the real world performance is much worse. I'm wondering if they're testing the model internally and didn't find anything wrong with the new parameter. I canceled my subscription and switched to a codex, but it's not as good. I'm tired of Anthropic changing things all the time. I us…

Claude is worse, they don't tell you when your experience has degraded and don't even let you use worse models if you run out any.

i mean, openai does same, even worse, they change the model, like gpt 5.4 to -mini

anthropic for now, at least just seems to change quantization of the model

Re: Anthropic downgraded cache TTL on March 6th

#347

Post by gib444 »

cassianoleal wrote: post #5

The title should be changed. It makes it look like they upped the TTL from 1 h to 5 months. The SI symbol for minutes is "min", not "M". A compromise would be to use the OP notation "m".

I love the title change that totally hides the scale of the issue. Good job poster/mods.

Re: Anthropic downgraded cache TTL on March 6th

#348

Post by siva7 »

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…

Anthropic has become shady as hell in less than a few weeks. The DoD Story and the overall popularity among developers got them a huge leap over OAI but i certainly won't renew my subscription with them. The Claude SDK feels like a constant fight against its own limitations compared to Codex and other Harnesses.

Re: Anthropic downgraded cache TTL on March 6th

#349

Post by glerk »

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.

Codex/GPT5.4 is just superior to Opus4.6 for coding. I swear it costs me 1/2 of the tokens to achieve the same results and it always follows through the plan to completion compared to Opus that takes shortcuts and sweeps things under the rug until I discover them through testing.

I'm not accusing anyone of foul play and I don't have financial interests in either company, but it feels like "something" within Code Claude/Anthropic models is optimizing to make you spend more tokens instead of helping you complete the task.

Re: Anthropic downgraded cache TTL on March 6th

#350

Post by throw_m239339 »

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…

Every single one of these AI services are running at loss, they are subsidized. Anybody who is surprised that these services are going to get degraded and their cost go up substantially learned nothing from the last 20 years of SAAS. It never gets cheaper.
Post reply on HN