I can agree. ChatGPT 5.5 made this a no-brainer choice. Anthropic are idiots removing Claude Code from the Pro plan. They need to ask Claude if what they did was a natural intelligence bug! Greed kills companies, too!
I cancelled Claude: Token issues, declining quality, and poor support
121–130 of 604 posts
Re: I cancelled Claude: Token issues, declining quality, and poor support
#122AI services are only minorly incentivized to reduce token usage. They want high token usage, it makes you pay more. They are going to continually test where the limit is, what is the max token usage before you get angry. All AI companies will continue to trade places for token use and cost as cost increases. We are in tepid water pretending it is a bath pretending we aren’t about to be boiled frogs.
People said this about AWS too. "Why would they save you money??". It turns out that every time they reduce prices, they make more money, because more people use their services.
AI companies have the same incentive. Make it cheaper and people will use it more, making you more money (assuming your price is still above cost). And of course they have every reason to reduce their on costs.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#123I use Claude Code with GLM, Kimi and MiniMax models. :) I was worried about Anthropic models quality varying and about Anthropic jacking up prices. I don't think Claude Code is the best agent orchestrator and harness in existence but it's most widely supported by plugins and skills.
Where are you getting inference from? I'm overwhelmed by the options at the moment.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#124Earlier quoted context omitted.
Indeed, I feel like we are in the early computer equivalent phase of AI, where giant expensive hardware is still required for frontier models. In 5 years I bet there will be fully open models we'll be able to run on a few $1000 of consumer hardware with equivalent performance to opus 4.7/4.6.
You'll never have the power of what they have though. Cloud capital is insane. So you can run 1 agent locally on $1k to $3k hardware They can run a fleet of thousands
I think intelligence per compute will go up significantly in the coming years, while the cost per compute will drop significantly. No way to know for sure, so I guess we'll see
Re: I cancelled Claude: Token issues, declining quality, and poor support
#125Earlier 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…
Unless you are getting outside of your comfort zone and taking a month off from your $200 subscription, every other month, I can’t see how you can make the universal claim that the open weights models are all 50% as good. Just today, DeepSeek released a new model, so nobody knows how that will compare, a week ago it was Gemma 4, etc. I’m okay with you making a comparison, but state the model and the timeframe in which it was tested that you are basing your conclusions on.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#126AI services are only minorly incentivized to reduce token usage. They want high token usage, it makes you pay more. They are going to continually test where the limit is, what is the max token usage before you get angry. All AI companies will continue to trade places for token use and cost as cost increases. We are in tepid water pretending it is a bath pretending we aren’t about to be boiled frogs.
That's what I am thinking, too. It sound's like a conspiracy theory, but at the end Anthropic et al benefits from models that don't finish their jobs. I recently read about this "over editing phenomenon". The machine is never done. It doesn't want to. It's like dating apps. They don't want you to find a good match, because then you cancel the subscription.
Which works fine, right up until China releases a new DeepSeek model that's 85% as capable as an Anthropic or OpenAI premium model but costs a fraction of what either of those US companies are charging.
Speaking of which:
https://www.cnbc.com/2026/04/24/deepseek-v4-llm-preview-open...
Re: I cancelled Claude: Token issues, declining quality, and poor support
#127Shameless 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 .
This is cool - just wanted to note https://marginlab.ai is one that has been around for a while.
are there any tools anyone knows to collect this kind of telemetry while using the tools instead of offline evals.
running evals seems like it may be a bit too expensive as a solo dev.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#128Yesterday 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…
Probably a silly idea, but I'll throw it into the mix - have your current AI build one for you. You can have exactly the coding agent you want, especially if you're looking for "extremely simple".
I got annoyed enough with Anthropic's weird behavior this week to actually try this, and got something workable up & running in a few days. My case was unique: there's no Claude Code for BeOS, or my older / ancient Macs, so it was easier to bootstrap & stitch something together if I really wanted an agentic coding agent on those platforms. You'll learn a lot about how models actually work in the process too, and how much crazy ridiculous bandaid patching is happening Claude Code. Though you might also appreciate some of the difficulties that the agent / harnesses have to solve too. (And to be clear, I'm still using CC when I'm on a platform that supports it.)
As for the llama_cpp vs Claude Code delays - I've run into that too. My theory is API is prioritized over Claude Code subscription traffic. API certainly feels way faster. But you're also paying significantly more.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#129Earlier quoted context omitted.
Maybe for folks who are deep into this, but it’s not exactly accessible. I tried reading up on it a couple of months ago, but parsing through what hardware I needed, the model and how to configure it (model size vs quantization), how I’d get access to the hardware (which for decent results in coding, new hardware runs $4k-$10k last I checked)—it had a non trivial barrier of entry. I was trying to do this over a long…
> 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 incidental and sporadic human intervention, you could even decrease that memory requirement a bit.)
Re: I cancelled Claude: Token issues, declining quality, and poor support
#130Claude 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.
I don't think i'd let it think more than 5 minutes without killing the process.