Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I cancelled Claude: Token issues, declining quality, and poor support

nickyreinert.de

Post reply on HN
Print view View original

171–180 of 604 posts

Re: I cancelled Claude: Token issues, declining quality, and poor support

#171

Post by Capricorn2481 »

cyanydeez wrote: post #69
vondur wrote: post #64

Wait, weren't there posts in the not too distant past where everyone was signing the praises for Claude and wondering how OpenAI will catch up?

Wait, are SaaS's fundamentally shifting business models searching to maximize the value of a product at the expense of a customer over time? Strange how things can change!

We've seen this sentiment shift on HN like 20 times in the past year, too often for it to be a real reflection of service quality. Feels more like people rooting for sports teams.

The services (OpenAI, Anthropic) are not wildly changing that much. People are just using LLMs more and getting frustrated because they were told it would change the world, and then they take it out on their current patron. Give it a month and we'll be hearing how far OpenAI has fallen behind.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#172

Post by binyu »

hungryhobbit wrote: post #167
binyu wrote: post #158

I feel like Anthropic is forcing their new model (Opus 4.7) to do much less guess work when making architectural choices, instead it prefers to defer back decisions to the user. This is likely done to mine sessions for Reinforcement-Learning signals which is then used to make their future models even smarter.

https://www.anthropic.com/engineering/april-23-postmortem On March 4, we changed Claude Code's default reasoning effort from high to medium to reduce the very long latency—enough to make the UI appear frozen—some users were seeing in high mode. This was the wrong tradeoff. We reverted this change on April 7 after users told us they'd prefer to default to higher intelligence and opt into lower effort for simple tasks.…

How does this address the point I moved specifically?

Re: I cancelled Claude: Token issues, declining quality, and poor support

#174

Post by janalsncm »

mrinterweb wrote: post #94

My recent frustration with Claude has been it feels like I'm waiting on responses more. I don't have historical latency to compare this with, but I feel like it has been getting slower. I may be wrong, and maybe its just spending more time thinking than it used to. My guess is Anthropic is having capacity issues. I hope I'm wrong because I don't want to switch.

There was a really good point in this podcast episode about the speed of LLMs. They are so slow that all of the progress messages and token streaming are necessary. But the core problem is that the technology is so darn slow.

https://podcasts.apple.com/us/podcast/this-episode-is-a-cogn...

As someone who both uses and builds this technology I think this is a core UX issue we’re going to be improving for a while. At times it really feels like a choose 2+ of: slow, bad, and expensive.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#175

Post by RealStupidity »

llm_nerd wrote: post #90
rectang wrote: post #47

I feel like I'm using Claude Opus pretty effectively and I'm honestly not running up against limits in my mid-tier subscriptions. My workflow is more "copilot" than "autopilot", in that I craft prompts for contained tasks and review nearly everything, so it's pretty light compared to people doing vibe coding. The market-leading technology is pretty close to "good enough" for how I'm using it. I look forward to the da…

I have Max 5x and use only Claude Opus on xhigh mode. I don't use agents, or even MCPs, and stick to Claude Code. I find it incredibly difficult to saturate my usage. I'm ending the average week at 30-ish percentage, despite this thing doing an enormous amount of work for (with?) me. Now I will say that with pro I was constantly hitting the limit -- like comically so, and single requests would push me over 100% for t…

If only OpenAI spent a significant amount of money on some kind of generative software that was predominantly trained on internet comments that'd be able to do all the astroturfing for them...

Re: I cancelled Claude: Token issues, declining quality, and poor support

#176

Post by SwellJoe »

zozbot234 wrote: post #129
root_axis wrote: post #112

Earlier quoted context omitted.

> new hardware runs $4k-$10k last I checked Starting closer to 40k if you want something that's practical. 10k can't run anything worthwhile for SDLC at useful speeds.

$10K should be enough to pay for a 512GB RAM machine which in combination with partial SSD offload for the remaining memory requirements should be able to run SOTA models like DS4-Pro or Kimi 2.6 at workable speed. It depends whether MoE weights have enough locality over time that the SSD offload part is ultimately a minor factor. (If you are willing to let the machine work mostly overnight/unattended, with only inci…

You can't put "SSD offload" and "workable speed" in the same sentence.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#177

Post by torstenvl »

I feel like almost everyone using AI for support systems is utterly failing at the same incredibly obvious place.

The first job of any support system—both in terms of importance and chronologically—is triage. This is not a research issue and it's not an interaction issue. It's at root a classification problem and should be trained and implemented as such.

There are three broad categories of interaction: cranks, grandmas, and wtfs.

Cranks are the people opening a support chat to tell you they have vital missing information about the Kennedy Assassintion or they want your help suing the government for their exposure to Agent Orange when they were stationed at Minot. "Unfortunately I can't help with that. We are a website that sells wholesale frozen lemonade. Good luck!"

Grandma questions are the people who can't navigate your website. (This isn't meant to be derogatory, just vivid; I have grandma questions often enough myself.) They need to be pointed toward some resource: a help page, a kb article, a settings page, whatever. These are good tasks for a human or LLM agent with a script or guideline and excellent knowledge/training on the support knowledge base.

WTFs are everything else. Every weird undocumented behavior, every emergent circumstance, every invalid state, etc. These are your best customers and they should be escalated to a real human, preferably a smart one, as soon as realistically possible. They're your best customers because (a) they are investing time into fixing something that actually went wrong; (b) they will walk you through it in greater detail than a bug report, live, and help you figure it out; and (c) they are invested, which means you have an opportunity for real loyalty and word-of-mouth gains.

What most AI systems (whether LLMs or scripts) do wrong is that they treat WTFs like they're grandmas. They're spending significant money on building these systems just to destroy the value they get from the most intelligent and passionate people in their customer base doing in-depth production QC/QA.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#178

Post by wood_spirit »

hungryhobbit wrote: post #163
wood_spirit wrote: post #149

Me and so many coworkers have been struggling with a big cognitive decline in Claude over the last two months. 4.5 was useful and 4.6 was great. I had my own little benchmark and 4.5 could just about keep track of a two way pointer merge loop whereas 4.6 managed a 3 way and the 1M context managed k-way. And this ability to track braids directly helped it understand real production code and make changes and be useful…

This was a real issue, and Anthropic recently awknowledged it: https://www.anthropic.com/engineering/april-23-postmortem Of course, it sucks when companies screw up ... but at the same time, they "paid everyone back" by removing limits for awhile, and (more importantly to me) they were transparent about the whole thing. I have a hard time seeing any other major AI provider being this transparent, so while I'm annoyed…

Yes that was one issue. It’s not the general degradation I have been talking about though, which is ongoing.

I recall reading similar tales of woe with other providers here on HN. I think the gradual dialling back of capability as capacity becomes strained as users pile on is part of the MO of all the big AI companies.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#179

Post by taytus »

ramoz wrote: post #109
taytus wrote: post #102

Earlier quoted context omitted.

I'd recommend Kimi k2.6 for your use. It is an excellent model at a fraction of the cost, and you can use Claude Code with it. I did a 1:1 map of all my Claude Code skills, and it feels like I never left Opus. Super happy with the results.

What provider do you use for Kimi

Straight from them, but I know other providers like io.net can be faster but I like to directly support the project.

Re: I cancelled Claude: Token issues, declining quality, and poor support

#180

Post by swader999 »

echelon wrote: post #68
Someone1234 wrote: post #51

Earlier quoted context omitted.

It feels more and more like OpenAI/Anthoropic aren't the future but Qwen, Kimi, or Deepseek are. You can run them locally, but that isn't really the point, it is about democratization of service providers. You can run any of them on a dozen providers with different trade-offs/offerings OR locally. They won't ever be SOTA due to money, but "last year's SOTA" when it costs 1/4 or less, may be good enough . More quantit…

Open Source isn't even within 50% of what the SOTA models are. Benchmarks are toys, real world use is vastly different, and that's where they seriously lag. Why should anyone waste time on poorer results? I'd rather pay my $200/mo because my time matters. I'm not a poor college student anymore, and I need more return on my time. I'm not shitting on open weights here - I want open source to win. I just don't see how t…

Also, this space will (and perhaps already is for some of us) be an arms race. Sure you can go local but hosted will always be able to offer more and if you want to be competitive, you'll need to be using the most capable.
Post reply on HN