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

211–220 of 604 posts

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

#211

Post by Capricorn2481 »

conrs wrote: post #162
Capricorn2481 wrote: post #157

Earlier quoted context omitted.

> 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…

I'm curious - why for now? This stuff is practically commoditized. Trying to think of anything that ever successfully got back into proprietary land from there.

It doesn't look commoditized to me, it looks subsidized. It looks like everyone is trying to be "the one" and running as competitively as possible until the others fail. Commoditized would imply these services are all going to mellow into a stable state and mostly compete on price. I don't think that's happening. These aren't paper clips, they are courting governments and trying to pull the ladder up behind them. That's why both Anthropic and OpenAI are preaching doomsday and trying to build a moat with regulations.

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

#212

Post by GodelNumbering »

drunken_thor wrote: post #20

AI 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 am betting on the fact that people will get increasingly frustrated at closed agent lock-ins. I built (cline fork) and open-sourced https://github.com/dirac-run/dirac with the sole focus on token efficiency expecting that the closed-lock-in vendors will do enough to frustrate their users over time. Looking for contributors

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

#214

Post by nancyminusone »

echelon wrote: post #68
Someone1234 wrote: post #51

Earlier quoted context omitted.

It feels more and more like OpenAI/Anthoropic aren't the future but Qwen, Kimi, or Deepseek are. You can run them locally, but that isn't really the point, it is about democratization of service providers. You can run any of them on a dozen providers with different trade-offs/offerings OR locally. They won't ever be SOTA due to money, but "last year's SOTA" when it costs 1/4 or less, may be good enough . More quantit…

Open Source isn't even within 50% of what the SOTA models are. Benchmarks are toys, real world use is vastly different, and that's where they seriously lag. Why should anyone waste time on poorer results? I'd rather pay my $200/mo because my time matters. I'm not a poor college student anymore, and I need more return on my time. I'm not shitting on open weights here - I want open source to win. I just don't see how t…

People pirate photoshop and office if they don't want to pay for it, making it as "free" as GIMP. If there is a free option people will use it. never underestimate the cheapskates.

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

#215

Post by fortyseven »

syhol wrote: post #33
zkmon wrote: post #21

Yesterday 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…

https://pi.dev/ seems popular, whats not open source about opencode? The repo has an MIT License.

Been LOVING Pi so far!

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

#216

Post by mescalito »

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.

I would also be interested on resources on "agents write most of your code" if you can share some.

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

#217

Post by pixelpoet »

llm_nerd wrote: post #90
rectang wrote: post #47

I 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…

I was in the same boat until last few days, where just a handful queries were enough to saturate my 5h session in about 30 mins.

Recently I've gotten Qwen 3.6 27b working locally and it's pretty great, but still doesn't match Opus; I've gotten check out that new Deepseek model sometime.

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

#219

Post by Oras »

amarcheschi wrote: post #43
wilbur_whateley wrote: post #2

Claude with Sonnet medium effort just used 100% of my session limit, some extra dollars, thought for 53 minutes, and said: API Error: Claude's response exceeded the 32000 output token maximum. To configure this behavior, set the CLAUDE_CODE_MAX_OUTPUT_TOKENS environment variable.

And on the seventh day, API Error: Claude's response exceeded the 32000 output token maximum

More on the 7th minute if you’re using opus

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

#220

Post by sidrag22 »

raincole wrote: post #183
rectang wrote: post #47

I 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…

> 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.

Post reply on HN