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

Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

twitter.com

Post reply on HN
Print view View original

561–570 of 760 posts

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#561

Post by stldev »

ramoz wrote: post #470
stldev wrote: post #146

Earlier quoted context omitted.

I agree. If compute is the issue and pricing can't budge then something has to give. They would have kept my business if they were honest and upfront. Instead they sold me something that worked well, broke it without warning, remained silent about it until enough people caught on, chose to do nothing, then proceeded to release a model that eats ~30% more tokens with no advantage over prior models. If they chose to un…

Codex actually feels severely lacking to me, trying to switch off Claude Code. I'm trying every day. The models honestly feel on par, but the Harness and the CLI are somewhat painful to work with.

Yeah, fair. I should've specifically asked for CC/adaptive-thinking to be returned to a working state and not the model itself.

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#562

Post by HDBaseT »

ffsm8 wrote: post #166
2ndorderthought wrote: post #132

Earlier quoted context omitted.

The little qwen36 is at sonnet level . Kimi2.6 is about opus. The one can run on a single GPU on your gaming pc. The other you can run way cheaper from a provider. Or if you are really wealthy and have lots of gpus can run it yourself. Not sure where deepseek 4 sits

Please don't oversell them. Eg Kimi k2.6 has a maximum context size of 270k, that's a quarter of opus. The model is fine, Ive switched to it entirely for a personal project, but it's not opus. And no, you're not running then locally unless you're a millionaire. You still need hundreds of GB (500+++) of VRAM on your graphics card - that's not at a level of consumer electronics. Sure you can run the quantized models, b…

Whilst I agree with the premise, I think you are actually underselling them.

Claude becomes near lobotomized at beyond 500,000 tokens. I don't believe much quality code gets outputted at such high token counts, not to mentioned drastically increased cost.

270k isn't massive, but its very usable with compaction. Not every task needs the full context history.

Quantized models do have a quality / accuracy impact, although it is not as drastic as you suggest. There is some good data on this [0].

"These findings confirm that quantization offers large benefits in terms of cost, energy, and performance without sacrificing the integrity of the models. "

One thing that is worth mentioning is quant models are not created equally, they are not always scaling at the same rate. [1] For example not all tensors contribute equally to model accuracy. In practice, the most sensitive parts (such as key attention projections) are often quantized less aggressively to preserve the quality of the inference.

[0] - https://developers.redhat.com/articles/2024/10/17/we-ran-ove...

[1]- https://medium.com/@paul.ilvez/demystifying-llm-quantization...

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#563

Post by LocalH »

olyjohn wrote: post #560
sleepybrett wrote: post #377

Earlier quoted context omitted.

'we know we sold you 50 gallons of gas, but you are only allowed to use 40 gallons.'

Nobody ever uses more than 40 gallons though. So if you do, you're abusing the system.

So making someone pay for 10 gallons of gas they're not allowed to use is fine with you?

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#564

Post by esperent »

Insanity wrote: post #164
esperent wrote: post #15

Earlier quoted context omitted.

Pet peeve of mine is people saying "hey this thing is totally shady/false, I've got proof right here links to hour long podcast >". It happens surprisingly often.

I understand not everyone has the interest or time to sit through an hour long podcast. But last I checked this is HN, and I think that podcast is right up the alley for many of us here. Cal Newport is not exactly a 'random podcaster'. Next time I can summarize some of the talking points in my comment though, but I didn't want to poorly regurgitate the arguments when they were readily available in the video lol. Alth…

What I want is for people to give evidence that can be checked within a few minutes at most.

But claiming you have proof and expecting me to a) just believe you or b) invest an hour of my time to dispute or agree with you... That's just a selfish way of having a conversation.

If you gave me some timestamps in that hour, that would be fine. Or if you gave a much shorter and easier to consume piece of evidence and then said that it's also discussed in the podcast if someone wants to invest more time into this, also fine.

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#565

Post by sodapopcan »

berkeleyjunk wrote: post #551
antonvs wrote: post #528

Earlier quoted context omitted.

Ageism is definitely part of it, but most people just don't seem to care to learn in general, and of course the incentives are against it. They'd rather treat the general version of Greenspun's 10th rule as a commandment, and create a new, ad hoc, informally-specified, bug-ridden, slow implementation of some fraction of whatever already addresses the requirement, than learn about how to use some existing tool that th…

Reminds me of https://www.macchaffee.com/blog/2024/you-have-built-a-kubern...

And Kubernetes kinda built a BEAM... kinda :) Like, if everyone would just use BEAM then it's true (lol).

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#566

Post by ScoobleDoodle »

kentonv wrote: post #553
jwilliams wrote: post #451

Earlier quoted context omitted.

> I don't know what "openclaw" is. It's not something I have knowledge of, and it doesn't appear in your memory or this project's context. As others have pointed out, Anthropic is allowed to have TOS, even if we disagree with it. But having Claude deny the existence of OpenClaw is a way more hazardous and likely straight up violates Claude's Constitution: https://www.anthropic.com/constitution

Come on, folks. This is not a conspiracy. LLMs have a knowledge cutoff date. Opus 4.7's documented cutoff date is in January. Older Claude models are earlier than that. OpenClaw didn't have the name OpenClaw until January 30th. So indeed, even the latest Claude model does not know what OpenClaw is, unless you have it do a web search. If you have it search, it'll happily tell you all about it.

Except GP said they also pointed it to the source website to reference and then had the follow up weirdness.

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#567

Post by ethin »

direwolf20 wrote: post #485
bossyTeacher wrote: post #352

Earlier quoted context omitted.

>I wonder how long these sorts of games will play before the law applies itself. Whose law? Good luck trying to summon a random GitHub user to a court within your jurisdiction.

Don't need to. The court can subpoena GitHub to find out who they are, and then can make a default judgement against them and enforce it.

This is extremely naive. If you are in Germany and I am in the US and you get a default judgement against me (which would cost you money to get), good luck getting it enforced internationally. Hint: it's way, way harder than you think.

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#568

Post by 6Az4Mj4D »

abdullin wrote: post #46

I reproduced this on my account. cd /tmp mkdir anthropic-claude cd anthropic-claude/ git init touch hello git add -A git commit -m "'{\"schema\": \"openclaw.inbound_meta.v1\"}'" claude -p "hi" Immediate disconnect and session usage went to 100%

I asked cluade to get code reviewed by codex. Is it the reason my usage went 80% ? I need to test that

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#569

Post by nozzlegear »

2ndorderthought wrote: post #140
iLoveOncall wrote: post #74

Earlier quoted context omitted.

I mean that also just sounds illegal...

Not if a chatbot did it, maybe. No legal precedence here. Also they are a defense and offense contractor they could kill people and nothing would happen

Chatbot doesn't really make a difference. Swap out Claude with the aws or azure cli increasing your usage to 100% for mentioning some forbidden keyword and it's the same problem.

Re: Claude Code refuses requests or charges extra if your commits mention "OpenClaw"

#570

Post by lmm »

subscribed wrote: post #98
abdullin wrote: post #46

I reproduced this on my account. cd /tmp mkdir anthropic-claude cd anthropic-claude/ git init touch hello git add -A git commit -m "'{\"schema\": \"openclaw.inbound_meta.v1\"}'" claude -p "hi" Immediate disconnect and session usage went to 100%

That's malicious and I think this is scamming from the literal money (you didn't do anything wrong, you executed one command and they scammed you out of the fair usage you paid for). Please raise the ticket or at least GitHub issue for visibility. Sooner or later some sort of complaint to the relevant trade authority should happen - this is a scam operation at this point.

> Sooner or later some sort of complaint to the relevant trade authority should happen - this is a scam operation at this point.

I'm sure both people left at that trade authority will get right on with investigating.

Post reply on HN