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

31–40 of 604 posts

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

#31

Post by dswalter »

varispeed wrote: post #10

It also seems to me they route prompts to cheaper dumber models that present themselves as e.g. Opus 4.7. Perhaps that's what is "adaptive reasoning" aka we'll route your request to something like Qwen saying it's Opus. Sometimes I get a good model, so I found I'll ask a difficult question first and if answer is dumb, I terminate the session and start again and only then go with the real prompt. But there is no guara…

You're describing a Taravangian prompt situation (a character in a book series who wakes up with a different/random intelligence level each day and has a series of tests for himself to determine which kind of decisions he's capable of that day). https://coppermind.net/wiki/Taravangian

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

#32

Post by pferdone »

jedisct1 wrote: post #26
zkmon wrote: post #21

Yesterday was a realization point for me. I gave a simple extraction task to Claude code with a local LLM and it "whirred" and "purred" for 10 minutes. Then I submitted the same data and prompt directly to model via llama_cpp chat UI and the model single-shotted it in under a minute. So obviously something wrong with coding agent or the way it is talking to LLM. Now I'm looking for an extremely simple open-source cod…

Swival is not bloated and was specifically made for local agents: https://swival.dev

pi.dev as well

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

#33

Post by syhol »

zkmon wrote: post #21

Yesterday was a realization point for me. I gave a simple extraction task to Claude code with a local LLM and it "whirred" and "purred" for 10 minutes. Then I submitted the same data and prompt directly to model via llama_cpp chat UI and the model single-shotted it in under a minute. So obviously something wrong with coding agent or the way it is talking to LLM. Now I'm looking for an extremely simple open-source cod…

https://pi.dev/ seems popular, whats not open source about opencode? The repo has an MIT License.

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

#34

Post by Larrikin »

jwaldrip wrote: post #5

I would love to just say that if you are using claude code, you should no be on pro. I feel like all the people complaining are complaining that an agent cant handle the work of a developer for $20/m. Get on at least max 5, its a world of a difference.

It's impossible to justify the jump in the expense unless you are directly working on something that makes you money. Messing around on a hobby project, doing some quick research, and getting personalized notifications was a no brainer for 200 a year.

The product keeps getting worse so I will definitely evaluate options and possibly switch if management keeps screwing up the product.

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

#35

Post by baq »

ModernMech wrote: post #30
GaryBluto wrote: post #25

Earlier quoted context omitted.

Luckily local AI is becoming more feasible every day.

I love how it's just a tacit understanding that these companies' entire MO is to carve out a territory, get everyone hooked on the good stuff and then jack up the price when they're addicted and captured -- literally the business plan of crack dealers, and it's just business as usual in the tech industry.

https://en.wikipedia.org/wiki/Enshittification 101

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

#37

Post by siliconc0w »

Shameless self plug but also worried about the silent quality regressions, I started building a tool to track coding agent performance over time.. https://github.com/s1liconcow/repogauge

Here is a sample report that tries out the cheaper models + the newest Kimi2.6 model against the 5.4 'gold' testcases from the repo: https://repogauge.org/sample_report.

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

#38

Post by gip »

janwillemb wrote: post #19

This is what worries me. People become dependent on these GenAI products that are proprietary, not transparant, and need a subscription. People build on it like it is a solid foundation. But all of a sudden the owner just pulls the foundation from under your building.

True. That is why it is key important to have open source and sovereign models that will be accessible to all and always on / local.

Competition (OpenAI vs Anthropic is fun to watch) and open source will get us there soon I think.

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

#39

Post by enraged_camel »

zkmon wrote: post #21

Yesterday was a realization point for me. I gave a simple extraction task to Claude code with a local LLM and it "whirred" and "purred" for 10 minutes. Then I submitted the same data and prompt directly to model via llama_cpp chat UI and the model single-shotted it in under a minute. So obviously something wrong with coding agent or the way it is talking to LLM. Now I'm looking for an extremely simple open-source cod…

I use both Cursor and Claude Code, and yes, the latter is noticeably slower with the same model at the same settings.

However, it's hard to justify Cursor's cost. My bill was $1,500/mo at one point, which is what encouraged me to give CC a try.

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

#40

Post by lanthissa »

for all the drama, its pretty clear both openai, google, and anthropic have had to degrade some of their products because of a lack of supply.

There's really no immediate solution to this other than letting the price float or limiting users as capacity is built out this gets better.

Post reply on HN