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

581–590 of 604 posts

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

#581

Post by bah9 »

dandaka wrote: post #554
dutchCourage wrote: post #198

Earlier quoted context omitted.

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.

It will come naturally! I have started with autocomplete as well. I was stumbling upon different problems and was fixing them by implementing best practices. Current stack is: 1/ Claude Code with yolo mode 2/ superpowers plugin 3/ red/green tdd 4/ a lot of planning and requirements before writing any code It feels like you always touch this edge of capability of models and your current workflow. Delegate more complex…

But... I am llm power user for more than a year and a half now. I cant delegate exactly because ive reviewed a lot of llm's code, and it is never good enough for me to step down from reviewing everything manually. I can understand how you can vibe code dashboard or tests, but vibe code your entire backend without checking it thru carefully? Madness.

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

#582

Post by echelon »

brazukadev wrote: post #551
echelon wrote: post #221

Earlier quoted context omitted.

Everyone is arguing why I'm wrong or that I should have presented more data. You've got the real insight with this claim. This is the way the world is moving. Open source isn't even going where the ball is being tossed. There is no leadership here. You're spot on. If the cost to deliver a unit of business automation is: A. $1M with human labor B. $700k human labor + open source models C. $500k human labor + $10,000 i…

This is you playing with imaginary numbers, like Sam Altman is doing for a long time. It won't end well.

I'm willing to bet that this is the shape of the future.

Wanna bet on it?

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

#583

Post by michaelmrose »

idiotsecant wrote: post #574
michaelmrose wrote: post #568

Earlier quoted context omitted.

You are assuming that somehow human creativity was born with intellectual property and will somehow die with it. It's just not so.

Ok captain pedant, instead of making vague handwavey negations exclusively how about you say something.

Intellectual property is supposed to feed creativity by securing for creators exclusive rights to benefit from their creation. It mostly feeds uncreative leaches whose business it is to own things in exchange for crumbs for the creativity and drags down both the inherent enjoyment of the fruits of creativity and even its creation. It belonged in the bin back when we first thought of it as is only going to be more unfit for purpose as time goes on.

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

#584

Post by brazukadev »

echelon wrote: post #582
brazukadev wrote: post #551

Earlier quoted context omitted.

This is you playing with imaginary numbers, like Sam Altman is doing for a long time. It won't end well.

I'm willing to bet that this is the shape of the future. Wanna bet on it?

It is not. Yeah I'm betting already. AI is changing software landscape but it won't be captured by openai and anthropic.

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

#585

Post by notjes »

janwillemb wrote: post #19

This 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.

Soon, a dented toaster will be enough to run decent models.

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

#587

Post by mufufu »

fsckboy wrote: post #358
raincole wrote: post #183

Earlier 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…

> 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.

You mean the regular electricity bill of your house and computer use? Computation runs on the cloud so not sure what you’re trying to argue here

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

#588

Post by stevenicr »

janalsncm wrote: post #379
onlyrealcuzzo wrote: post #294

Earlier 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…

How can a person reconcile this comment with the one at the root of this thread? One person says Claude struggles to even meet the strict requirements of a spec sheet, another says Claude is doing a great job and doesn’t even need specific specs? I have my own anecdata but my comment is more about the dissonance here.

I think it matters what the project and tech stack is, and how much you try to get done before starting a fresh chat.

I've had interesting chats where it explained that it's choice of tailwind for example was because it had a ton of training knowledge on it.

I've also had it try to build more in one chat than it should many times.

For some reason openai codex handles building too much without failing better - but that is total anecdata from my particular projects and ymmv.

I've had these things try to build big when a little nudge gets them to change direction and not build so much. Explain which libraries and such and asking it to change the tech stack and the steps to build at once seem to make things much better for my use cases.

Also running extra checks and cleanup later is a thing, that sure a human might have seen an obvious thing at time of build, but we have bigger memory context comparatively imho.

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

#589

Post by partomniscient »

Capricorn2481 wrote: post #157
jjfoooo4 wrote: post #142

Earlier quoted context omitted.

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 willin…

>Of course, many people are building their business on huge AI scaffolding.

It's similar in the way many businesses transitioned their scalability etc. to 'the cloud' starting a couple of decades ago.

It's a combination of loss of control and abdication of responsibility. They can claim to the customer the reason the service went down is now Microsofts or Amazons etc. etc. fault. Ultimately the end-user was the one that ended up losing.

It was a choice. There was something they could do - and keep everything in house, although cost-competiveness becomes an issue at some point and you get priced out of your target market. Everyone loses except for the cloud computing (or now AI) providers.

Post reply on HN