I cancelled Claude: Token issues, declining quality, and poor support • Hacker News Board

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

#21

Post by zkmon » Fri, Apr 24, 2026, 4:41 PM UTC

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 coding agent. Nanocoder doesn't seem install on my Mac and it brings node-modules bloat, so no. Opencode seems not quite open-source. For now, I'm doing the work of coding agent and using llama_cpp web UI. Chugging it along fine.

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

#22

Post by drunken_thor » Fri, Apr 24, 2026, 4:41 PM UTC

giancarlostoro wrote: post #17

wilbur_whateley wrote: post #2

Claude with Sonnet medium effort just used 100% of my session limit, some extra dollars, thought for 53 minutes, and said: API Error: Claude's response exceeded the 32000 output token maximum. To configure this behavior, set the CLAUDE_CODE_MAX_OUTPUT_TOKENS environment variable.

You're using it within their high usage rate window. I hope you're aware of this, if you use it out of the high usage time window it's supposed to use less, but it does seem a little odd that Sonnet uses so much, even on Medium.

Ah so we are only supposed to use this work tool outside of work hours?

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

#23

Post by hedgehog » Fri, Apr 24, 2026, 4:42 PM UTC

I used Opus via Copilot until December and then largely switched over to Claude Code. I'm not sure what the difference is but I haven't seen any of these issues in daily use.

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

#24

Post by bad_haircut72 » Fri, Apr 24, 2026, 4:42 PM UTC

Waiting 60s every time I send a msg really kills the ux of claude

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

#25

Post by GaryBluto » Fri, Apr 24, 2026, 4:42 PM UTC

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.

Luckily local AI is becoming more feasible every day.

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

#26

Post by jedisct1 » Fri, Apr 24, 2026, 4:42 PM UTC

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

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

#27

Post by giancarlostoro » Fri, Apr 24, 2026, 4:42 PM UTC

zendarr wrote: post #7

Seems like some of the token issues may be corrected now https://www.anthropic.com/engineering/april-23-postmortem

The problem is they changed people's default settings, and if you're like me, you keep a Claude Code session open for days, maybe weeks and even a month, and just come back to it and keep going. I wouldn't be surprised if there's hundreds if not thousands of people still on these broken configurations / models.

Dear Anthropic:

Please, for the love of all things holy, NEVER change someone's defaults without INFORMING the end user first, because you will wind up with people confused, upset, and leaving your service.

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

#28

Post by bauerd » Fri, Apr 24, 2026, 4:43 PM UTC

They can't afford to care about individual customers because enterprise demand exploded and they're short on compute

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

#29

Post by aleqs » Fri, Apr 24, 2026, 4:43 PM UTC

The usage metering is just so incredibly inconsistent, sometimes 4 parallel Opus sessions for 3 hours straight on max effort only uses up 70% of a session, other times 20 mins / 3 prompts in one session completely maxes it out. (Max x20 plan) Is this just a bug on anthropic side or is the usage metering just completely opaque and arbitrary?

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

#30

Post by ModernMech » Fri, Apr 24, 2026, 4:44 PM UTC

GaryBluto wrote: post #25

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.

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.