I also cancelled my subscription.The $20 Pro plan has become completely unusable for any real work. What is especially frustrating is that Claude Chat and Claude Code now share the exact same usage limits — it makes zero sense from a product standpoint when the workflows are so different. Even the $200 Max plan got heavily nerfed. What used to easily last me a full week (or more) of solid daily use now burns out in just a few days. Combined with the quality drop and unpredictable token consumption, it simply stopped being worth it.
I cancelled Claude: Token issues, declining quality, and poor support
151–160 of 604 posts
Re: I cancelled Claude: Token issues, declining quality, and poor support
#152I've noticed that sometimes the same Claude model will make logical errors sometimes but not other times. Claude's performance is highly temporal. There's even a graph! https://marginlab.ai/trackers/claude-code/ I haven't seen anyone mention this publicly, but I've noticed that the same model will give wildly different results depending on the quantization. 4-bit is not the same as 8-bit and so on in compute requirem…
I'm not sure that graph shows a time-based correlation. The 60% line stays inside the 95% confidence interval. Is that not just a measurement of noise?
Re: I cancelled Claude: Token issues, declining quality, and poor support
#153I've spent thousands of dollars on API tokens in the last few months. Out of my own pocket, as an indie contractor. I used the API specifically instead of Pro/Max/Plus/Silver/Gold/Platinum/Diamond to avoid all of the mess there regarding usage resets and potential hidden routing to worse models. It worked great for months, I got a ton of shit done, shipped a bunch of features. I really began to rely on the tech. I wa…
The thing that irks me the most is that I was paying full price. Literally spreading my cheeks wide open and saying, "here ya go Anthropic, all yours." and for actually close to a year it was great. Looking back I see I began using it in March of 2025. Thats roughly a year of integrating it into my day to day, pairing with it constantly, and as I said shipping really well engineered meaningful work.
They could have just kept doing this - literally printing money. Literally: do absolutely nothing, go on vacation, profit $$$. So why did so much change? I think that the issue is they were trying to optimize CC for the monthly plan folks, the ones who are likely losing the company money, but API users became collateral damage.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#154I 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…
Similar with the copilot and not autopilot usage. I find its the best of them all. Mostly i just use it as an occasionnal search engine. I've never found LLMs to be efficient to actually do work. I do miss the day when tech docs were usable. Claude seems like a crutch for gaps in developer experience more than anything.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#155Me 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…
did you set your 4.7 to xhigh or max effort? anything else is basically not worth your time...
Re: I cancelled Claude: Token issues, declining quality, and poor support
#156Sometimes it feels like Anthropic uses token processing as a throttling tool, to their advantage.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#157This 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.
But these products are all drop in replacements for each other. I've recently favored Codex more than CC, just because rate limits got mildly annoying. I really didn't have to change anything about my workflow in doing that.
> But these products are all drop in replacements for each other
For now. That doesn't really change the risk, that just means they are all hyper competitive right this moment, and so they are comparable. If one of them becomes king of the hill, nothing stops them from silently degrading or jacking prices.
The only shield is to not be dependent in the first place. That means keeping your skills sharp and being willing to pass on your knowledge to juniors, so they aren't dependent on these things.
Of course, many people are building their business on huge AI scaffolding. There's nothing they can do.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#158I 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.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#159I 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…
Yea, I never got how people are even able to hit the weekly limits so consistently. Maybe it's because they use it for work? But in that case, you would expect the employer to cover it so idk.
>I'm super skeptical of the influx of "DAE think Opus sucks now. Let's all move to Codex!" nonsense that has flooded HN. A part of it is the ex-girlfriend thing where people are angry about something and try to force-multiply their disagreement, but some of it legitimately smells like astroturfing. Like OpenAI got done pay $100M for some unknown podcaster and start hiring people to write this stuff online.
A lot of people are angry about the whole openclaw situation. They are especially bitter that when they attempted to justify exfiltrating the OAuth token to use for openclaw, nobody agreed with them that they had the right to do so, and sided with Claude that different limits for first-party use is standard. So they create threads like this, and complain about some opaque reason why Anthropic is finished (while still keeping their subscription, of course).
Re: I cancelled Claude: Token issues, declining quality, and poor support
#160Yesterday 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…
You can run CC with local models, it's pretty straightforward. I've done this with vLLM + a thin shim to change the endpoint syntax.