Biggest issue i see is, models are not getting efficient. This is no where going to get commoditised. There will be a limit at which you can burn money at subsidised cost.
I cancelled Claude: Token issues, declining quality, and poor support
301–310 of 604 posts
Re: I cancelled Claude: Token issues, declining quality, and poor support
#302I don't get it. I use Claude Code every day, what I would consider pretty heavy usage...at least as heavy as I can use it while actually paying attention to what it's producing and guiding it effectively into producing good software. I literally never run into usage limits on the $100 plan, even when the bugs related to caching, etc. were happening that led to inflated token usage. WTF are y'all doing that chews toke…
I would say most people are complaining about the $20 plan, which is now actually indistinguishable from the free one. I tested it and ran into limits immediately. With Max, i can work properly again.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#303Earlier quoted context omitted.
> the day when LLM-assisted coding is commoditized Like yesterday? LLM-assisted coding is $100/mo. It looks very commoditized when most houses in developed world pay more for electricity than that. My definition of LLM-assisted coding is that you fully understand every change and every single line of the code. Otherwise it's vibe coding. And I believe if one is honest to this principle, it's very hard to deplete the…
> fully understand every change and every single line of the code. im probably just not being charitable enough to what you mean, but thats an absurd bar that almost nobody conforms to even if its fully handwritten. nothing would get done if they did. But again, my emphasis is on that im probably just not being charitable to what you mean.
I mean "understanding it just like when you hand wrote the code in 2019."
Obviously I don't mean "understanding it so you can draw the exact memory layout on the white board from memory."
Re: I cancelled Claude: Token issues, declining quality, and poor support
#304Earlier quoted context omitted.
> the day when LLM-assisted coding is commoditized Like yesterday? LLM-assisted coding is $100/mo. It looks very commoditized when most houses in developed world pay more for electricity than that. My definition of LLM-assisted coding is that you fully understand every change and every single line of the code. Otherwise it's vibe coding. And I believe if one is honest to this principle, it's very hard to deplete the…
> fully understand every change and every single line of the code. im probably just not being charitable enough to what you mean, but thats an absurd bar that almost nobody conforms to even if its fully handwritten. nothing would get done if they did. But again, my emphasis is on that im probably just not being charitable to what you mean.
You don't understand every change you make in the PRs you offer for review?
Re: I cancelled Claude: Token issues, declining quality, and poor support
#305Earlier quoted context omitted.
> Stop trying to use it as all-or-nothing. You can still make the decisions, call the shots, write code where AI doesn't help and then use AI to speed up parts where it does help. You're assuming that finding the places where AI needs help isn't already a larger task than just writing it yourself. AI can be helpful in development in very limited scenarios but the main thrust of the comment above yours is that it take…
> You're assuming that finding the places where AI needs help isn't already a larger task than just writing it yourself. Not assuming anything, I'm well versed in how to do this. Anyone who defers to having AI write massive blocks of code they don't understand is going to run into this. You have to understand what you want and guide the AI to write it. The AI types faster than me. I can have the idea and understand a…
You've come full circle and are essentially just describing what the OP was saying in their initial post lol.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#306I 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…
> the day when LLM-assisted coding is commoditized Like yesterday? LLM-assisted coding is $100/mo. It looks very commoditized when most houses in developed world pay more for electricity than that. My definition of LLM-assisted coding is that you fully understand every change and every single line of the code. Otherwise it's vibe coding. And I believe if one is honest to this principle, it's very hard to deplete the…
In industry, the cost is more than 100/mo for engineers. With increased adoption and what I know now, I expect full time devs to rack up $500-$2000 usage bills if they're going full parallel agentic dev. Personal usage for projects and non-production software is not a benchmark IMO
Re: I cancelled Claude: Token issues, declining quality, and poor support
#307Earlier quoted context omitted.
> With hard requirements listed, I found out that the generated code missed requirements, This is hardly a surprise, no? No matter how much training we run, we are still producing a generative model. And a generative model doesn't understand your requirements and cross them off. It predicts the next most likely token from a given prompt. If the most statistically plausible way to finish a function looks like a versio…
But agents do keep task lists and check the tasks off as they go. Of course it’s not perfect either but it’s MUCH better than an LLM can offer on its own. If you are seeing an agent missing tasks, work with it to write down the task list first and then hold it accountable to completing them all. A spec is not a plan.
bro do you really not understand that that's a game played for your sake - it checks boxes yes but you have no idea what effect the checking of the boxes actually has. like do you not realize/understand that anthropic/openai is baking this kind of stuff into models/UI/UX to give the sensation of rigor.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#308Anthropic is astroscaling. We're essentially buying into a loop where speed and iteration take precedence over stability and support. If you view them as an experimental lab undergoing rapid atmospheric friction rather than a company, the "unreliability" is just the cost of being at the frontier. This is not an endorsement for Anthropic, just imagining their craziness on how you "can" grow in a fraction of time.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#309I 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…
> the day when LLM-assisted coding is commoditized Like yesterday? LLM-assisted coding is $100/mo. It looks very commoditized when most houses in developed world pay more for electricity than that. My definition of LLM-assisted coding is that you fully understand every change and every single line of the code. Otherwise it's vibe coding. And I believe if one is honest to this principle, it's very hard to deplete the…
Commoditization will be complete for my purposes when an LLM trained on a legitimately licensed corpus can achieve roughly what Opus 4.5+ or the highest powered GPTs can today.
I anticipate a Napster-style reckoning at some point when there's a successful high-profile copyright suit around obviously derivative output. It will probably happen in video or imagery first.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#310I feel like Opus 4.5 was the peak in Claude Code usefulness. It was smart, it was interactive, it was precise. In 4.6 and 4.7, it spends a long time thinking and I don't know what's happening, often hits a dead-end and just continues. For a while I was setting Opus 4.5 in Claude Code, but it got reset often. I just canceled my Max plan, don't know where to look for alternatives.