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

81–90 of 447 posts

Re: Anthropic downgraded cache TTL on March 6th

#81

Post by cyanydeez »

PunchyHamster wrote: post #56
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.

Why would any company release open weights once the investment money stops ? Releasing open weights have been basically a PR move, the moment those companies need to actually make money they will cut it out as that reduces their client base. They DO NOT want you to run AI. They want you to pay them to do it

open weights is a way to nerf your opponent and is meaningless to your business if you need to retrain a model because your trailing

So, it makes a lot of sense to get people a "demo" and claim the paid product is better.

i think a lot of people have no idea how capable local models are atm.

Re: Anthropic downgraded cache TTL on March 6th

#82

Post by simianwords »

officialchicken wrote: post #69
simianwords wrote: post #29

Earlier quoted context omitted.

The enshittification meme has been taken too seriously to the point where it is shoehorned into every single place possible. It is not in the interests for Anthropic to screw its customer base. Running a frontier lab comes with tradeoffs between training, inference and other areas.

The investors are their customers - not the users of the end-product.

This shows a lack of understanding of how markets work. Investors make money when the valuation of the company increases. The valuation of the company is the best prediction of future profit risk adjusted.

How would anthropic increase future profits without satisfying customers?

Re: Anthropic downgraded cache TTL on March 6th

#83

Post by oezi »

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…

On OpenRouter token consumption is up 5x since November 2025. If this is indicative of the industries growth then I can't fathom how we will not hit resource constraints.

Re: Anthropic downgraded cache TTL on March 6th

#84

Post by cedws »

politelemon wrote: post #76
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…

Why were third party harnesses banned? Surely they'd want sticking power over the ecosystem.

There’s the argument that Anthropic has built Claude Code to use the models efficiently, which the subscription pricing is based on.

Maybe there’s some truth to that, but then why haven’t OpenAI made the same move? I believe the main reason is platform control. Anthropic can’t survive as a pipeline for tokens, they need to build and control a platform, which means aggressively locking out everybody else building a platform.

Re: Anthropic downgraded cache TTL on March 6th

#85

Post by taffydavid »

This is the same shit openAI used to do last year, quietly downgrading their offerings while hyping the next big thing. I thought Anthropic were different but it seems they're playing the exact same long con with Mythos.

They can't really revolutionize AI again so they make the product worse and worse and then offer you a "better" one

Re: Anthropic downgraded cache TTL on March 6th

#86

Post by lukan »

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…

" or if it just can't solve everything yet."

Obviously it cannot. But if you give the AI enough hints, clear spec, clear documentation and remove all distracting information, it can solve most problems.

Re: Anthropic downgraded cache TTL on March 6th

#87

Post by cyanydeez »

hhh wrote: post #79
ramon156 wrote: post #66

Earlier quoted context omitted.

can a druggie stop using when the quality is too poor? I get your analogy, but it doesn't apply here

[flagged]

the parallel druggie are the AI companies who want to quit burning cash but tealize their users are all addicted to 40k GPUs that cost $100s dollars a month to use and theres no way to train a SOTA model better and guarantee better efficiency; so you promo double tokens as a cover for a QUANT downgrade while publishing a reskinned "upgrade" as super killer AI hoping some B2B will take a hit of the crack pipe.

Re: Anthropic downgraded cache TTL on March 6th

#88

Post by jhancock »

PunchyHamster wrote: post #56
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.

Why would any company release open weights once the investment money stops ? Releasing open weights have been basically a PR move, the moment those companies need to actually make money they will cut it out as that reduces their client base. They DO NOT want you to run AI. They want you to pay them to do it

ok. maybe. I don't know. I'm asking how you know.

z.ai did go public on the HK exchange. They are under pressures similar to other public companies.

I know that China models are increasingly being trained and run using Huawei chips instead of Nvidia. I know China has a surplus of electricity from renewables (wind, solar, hydro).

Re: Anthropic downgraded cache TTL on March 6th

#89

Post by cyanydeez »

PunchyHamster wrote: post #63
simianwords wrote: post #18

There’s a case for intelligent caching: coarse grained 1h and 5min type TTls are not optimal.

Caching LLM is not like caching normal content; the longer it is the more beneficial it is and it only stops being worth when user stops current session. So you'd need some adaptive algorithm to decide when to keep caching and when to purge it whole, possibly on client side, but if you give client the control, people will make it use most cache possible just to chase diminishing returns. So fine grained control here…

keep in mind, efficient KV caching needs to be next to the GPU, so you sls need you HA to keep routing the user to the same hardware.

the hardware VM model is almost identical. Each session can go anywhere to start but a live session cant just be routed anywhere without penalty.

Post reply on HN