Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

nickyreinert.de

Post reply on HN
Print view View original

281–290 of 604 posts

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

#281

Post by kakacik »

Aurornis wrote: post #256
munk-a wrote: post #247

Earlier 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…

If you are trying to sell it, you are doing a poor job and effectively siding with OP while desperately trying to write the opposite.

Juniors are mostly better than what you write as behavior, I certainly never had to correct as much after any junior as OP writes. If you have 'boring code' in your codebase, maybe it signals not that great architecture (and I presume we don't speak about some codegens which existed since 90s at least).

Also, any senior worth their salt wants to intimately understand their code, the only way you can anyhow guarantee correctness. Man, I could go on and on and pick your statements one by one but that would take long.

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

#282

Post by dannersy »

wg0 wrote: post #202

I 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…

Beautifully stated and I couldn't agree more. This is my experience.

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

#283

Post by Aurornis »

rafram wrote: post #271
Aurornis wrote: post #258

Earlier quoted context omitted.

> It’s pretty funny to claim that a model released 22 hours ago is the bare minimum requirement for AI-assisted programming. Not what I said. The OP was trying to write specs and have an AI turn it into an app, then getting frustrated with the amount of cleanup. If you want the AI to write code for you and minimize your cleanup work, you have to use the latest models available. They won't be perfect, but they're goin…

Is it actually the case that 5.5 is that much better at implementing specs than its very capable predecessor released a month ago? Just seems like a baseless and silly claim about a model that has barely been out long enough for anyone to do serious work with it.

> Is it actually the case that 5.5 is that much better at implementing specs than its very capable predecessor released a month ago?

The OP comment was talking about Claude Sonnet. I was comparing to that.

I should have just said "use the best model available"

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

#284

Post by sidrag22 »

Maxatar wrote: post #257
sidrag22 wrote: post #220

Earlier quoted context omitted.

> 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're most likely being pedantic, like when someone says they understand every single line of this code: x = 0 for i in range(1, 10): x += i print(x) They don't mean they understand silicon substrate of the microprocessor executing microcode or the CMOS sense amplifiers reading the SRAM cells caching the loop variable. They just mean they can more or less follow along with what the code is doing. You don't need to b…

you drew it to its most uncharitable conclusion for sure, but ya thats pretty much the point i was making.

How deep do i need to understand range() or print() to utilize either, on the slightly less extreme end of the spectrum.

But ya, im pretty sure its a point that maybe i coulda kept to myself and been charitable instead.

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

#285

Post by petterroea »

alex-onecard wrote: post #182
petterroea wrote: post #53

Looking at Anthropic's new products I think they understand they don't really have a cutting edge other than the brand. I tried Kimi 2.6 and it's almost comparable to Opus. Anthropic lost the ball. I hope this is a sign the we are moving towards a future where model usage is a commodity with heavy competition on price/performance

How are you using kimi 2.6? I am considering their coding plan to replace my claude max 5x but I am worried about privacy and security.

I'm only using it for a project I'm already expecting to open source later. Don't think I'm comfortable using it for more private work

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

#286

Post by rob »

wg0 wrote: post #202

I 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…

I use the "Superpowers" plugin that creates an initial spec via brainstorming together, and then takes that spec and creates an implementation spec file based on your initial spec. It also has other agents make sure the spec doesn't drift between those two stages and does its own self-reviews. Almost every time, it finds and fixes a bunch of self-review issues before writing the final plan. Then I take that final plan and run it through the actual execution phase that does its own reviews after everything.

Just saying that I know a lot of people like to raw dog it and say plugins and skills and other things aren't necessary, but in my case I've had good success with this.

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

#287

Post by adamors »

dostick wrote: post #275

The discussion about Claude always omit the important context - which language/platform you’re using it for. It is best trained for web languages and has most up to date knowledge for that. If you use it for Swift it is trained on whole landfill of code and that gives you strong bias towards pre-Swift 6 coding output. Imagine you would give Claude a requirements for a web app, and it implements it all in JQuery. That…

It’s not ommited, OP clearly talks about editing Javascript.

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

#288

Post by mwigdahl »

system2 wrote: post #54

Same here. The single prompt burnt all my tokens in 3 minutes for the day. What happened to Claude in the last 2 months? I was happy with what they were providing and was happy to pay whatever for it. Why did they mess with it? Why are they destroying the tool we all loved? I hate enshittification and I hate seeing this happening to Claude Code right now.

What level of subscription are you on? If you're complaining about running out of tokens but are happy to pay "whatever" for it, it should be Max 20x, yes? And one prompt drained all your tokens for the day on Max 20x?

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

#289

Post by sroerick »

dutchCourage wrote: post #198
dandaka wrote: post #145

Earlier quoted context omitted.

autopilot (yolo mode) is amazing and feels great, truly delegate instead of hand-holding on every step

Do you have any good resources on how to work like that? I made the move from "auto complete on steroids" to "agents write most of my code". But I can't imagine running agents unchecked (and in parallel!) for any significant amount of time.

Right now, I'm finding a decent rhythm in running 10-20 prompts and then kind of checking the results a few different ways. I'll ask the agent to review the code, I'll go through myself, I'll do some usability and gut checks.

This seems to be a good window where I can implement a pretty large feature, and then go through and address structural issues. Goofy thinks like the agent adding an extra database, weird fallback logic where it ends up building multiple systems in parallel, etc.

Currently, I find multiple agents in parallel on the same project to be not super functional. Theres just a lot of weird things, agents get confused about work trees, git conflicts abound, and I found the administrative overhead to be too heavy. I think plenty of people are working on streamlining the orchestration issue.

In the mean time, I combat the ADD by working on a few projects in parallel. This seems to work pretty well for now.

It's still cat herding, but the thing is that refactors are now pretty quick. You just have to have awareness of them

I was thinking it'd be cool to have an IDE that did coloring of, say, the last 10 git commits to a project so you could see what has changed. I think robust static analysis and code as data tools built into an IDE would be powerful as well.

The agents basically see your codebase fresh every time you prompt. And with code changes happening much more regularly, I think devs have to build tools with the same perspective.

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

#290

Post by swdunlop »

hungryhobbit wrote: post #163
wood_spirit wrote: post #149

Me 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…

This was a real issue, and Anthropic recently awknowledged it: https://www.anthropic.com/engineering/april-23-postmortem Of course, it sucks when companies screw up ... but at the same time, they "paid everyone back" by removing limits for awhile, and (more importantly to me) they were transparent about the whole thing. I have a hard time seeing any other major AI provider being this transparent, so while I'm annoyed…

Amusingly, when a coworker was looking for this postmortem, they found a different postmortem of three Claude issues that caused decay. This one was in the platform, not in Claude Code:

https://www.anthropic.com/engineering/a-postmortem-of-three-...

I think there's a certain amount of running with scissors going on here. I appreciate the transparency, but the time to remediation here seems pretty long compared to the rate of new features.

Post reply on HN