AI has a lot of future potential but at every level... it's still not very good. And certainly not good enough to validate the expense, let alone what the actual cost would be were it profitable.
I cancelled Claude: Token issues, declining quality, and poor support
351–360 of 604 posts
Re: I cancelled Claude: Token issues, declining quality, and poor support
#352I 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!
>removing Claude Code from the Pro plan Wait really? I wanted to give it a try, but for $200 a month no way am I paying that for something I just want to experiment around with
Let me take this back - you are probably grandfathered into having Claude Code in your Pro plan though! Now I feel sorry I upgraded to Max as I could've kept Pro, just in case, but now I will just have to cancel it if I want to move to ChatGPT, or Gemini 4 when it's out, and if it's worth it. They need to consult with AI when making such stupid choices, honestly!
Re: I cancelled Claude: Token issues, declining quality, and poor support
#353Signup for all major providers (pro plan) and round-robin between all of them. This is the only way to protect against not having access to all of these heavily subsidised subscriptions. See what happened to Copilot.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#354I write detailed specs. Multifile with example code. In markdown. Then hand over to Claude Sonnet. With hard requirements listed, I found out that the generated code missed requirements, had duplicate code or even unnecessary code wrangling data (mapping objects into new objects of narrower types when won't be needed) along with tests that fake and work around to pass. So turns out that I'm not writing code but I'm r…
This is how I feel with AI math proofs. I’m not sure where they’re at now, but a year ago it took so much more time to check if an LLM proof was technically correct even if hard to understand, compared to a well structured human proof.
Maybe it was Timothy Gowers who commented on this.
Lots of human proofs have the unfortunate “creative leap” that isn’t fully explained but with some detectable subtlety. LLMs end up making large leaps too, but too often the subtle ways mathematicians think and communicate is lost, and so the proof becomes so much more laborious to check.
Like you don’t always see how a mathematician came up with some move or object to “try”, and to an LLM it appears random large creative leaps are the way to write proofs.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#355Yesterday 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'd figure by now we would have something between a TUI and an IDE.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#356Earlier quoted context omitted.
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.
Not to knee jerk on a bro comment, but, bro.. Are you seriously saying that breaking a large complex problem down into it's constituent steps, and then trying to solve each one of them as an individual problem is just a sensation of rigour?
I believe they're saying that the checkboxes are window dressing, not an accurate reflection of what the LLM has done.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#357I write detailed specs. Multifile with example code. In markdown. Then hand over to Claude Sonnet. With hard requirements listed, I found out that the generated code missed requirements, had duplicate code or even unnecessary code wrangling data (mapping objects into new objects of narrower types when won't be needed) along with tests that fake and work around to pass. So turns out that I'm not writing code but I'm r…
This may be a bit silly but I do what you do and then I tell Claude to review the code it wrote and compare it to the specs. It will often find issues and fix it. Then I review the reviewed code, and it's leagues better than pre reviewed code.
This may be worth trying out.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#358I 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…
>LLM-assisted coding is $100/mo. It looks very commoditized when most houses in developed world pay more for electricity than that.
this is a small nit, but you still have to pay your electric bill, the $100/mo is on top of that. if you're doing cost accounting you don't want to neglect any costs. Just because you can afford to lease a car, doesn't mean you can afford to lease a 2nd car.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#359Earlier quoted context omitted.
> Or just don't use AI to write code. Anecdata, but I'm still finding CC to be absolutely outstanding at writing code. It's regularly writing systems-level code that would take me months to write by hand in hours, with minimal babysitting, basically no "specs" - just giving it coherent sane direction: like to make sure it tests things in several different ways, for several different cases, including performance, comp…
> basically no "specs" - just giving it coherent sane direction This is one variable I almost always see in this discussion: the more strict the rules that you give the LLM, the more likely it is to deeply disappoint you The earlier in the process you use it (ie: scaffolding) the more mileage you will get out of it It's about accepting fallability and working with it, rather than trying to polish it away with care
To me this still feels like it would be a net negative. I can scaffold most any project with a language/stack specific CLI command or even just checking out a repo.
And sure, AI could “scaffold” further into controllers and views and maybe even some models, and they probably work ok. It’s then when they don’t, or when I need something tweaked, that the worry becomes “do I really understand what’s going on under the hood? Is the time to understand that worth it? Am I going to run across a small thread that I end up pulling until my 80% done sweater is 95% loose yarn?”
To me the trade-off hasn’t proven worth it yet. Maybe for a personal pet project, and even then I don’t like the idea of letting something else undeterministically touch my system. “But use a VM!” they say, but that’s more overhead than I care for. Just researching the safest way to bootstrap this feels like more effort than value to me.
Lastly, I think that a big part of why I like programming is that I like the act of writing code, understanding how it works, and building something I _know_.
Re: I cancelled Claude: Token issues, declining quality, and poor support
#360AI 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.
I severely doubt it. Token spend translates to real cost for the provider. Each token involves real and expensive compute. They aren't free monopoly money you get billed arbitrarily for. You're paying for electricity and infrastructure involved in generating each token.
Less spend means less real cost to the provider while your flat monthly subscription stays the same price. As well, reducing token use per customer means you can over-subscribe even harder, allowing for more flat monthly subscriptions.
Less tokens = more free capacity = more subscription income.