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

Anthropic says OpenClaw-style Claude CLI usage is allowed again

docs.openclaw.ai

Post reply on HN
Print view View original

251–260 of 318 posts

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#251

Post by giancarlostoro »

Alifatisk wrote: post #28

> Anthropic staff told us OpenClaw-style Claude CLI usage is allowed again Anthropic staff have had contradictive statements in Twitter and have corrected each other. Their intent for clarifications lead to confusion. > OpenClaw treats Claude CLI reuse and claude -p usage as sanctioned for this integration unless Anthropic publishes a new policy. Oh cool, so everything is back to business now, until they all or sudde…

They need to stop announcing this on freaking Twitter and make a formal announcement on their blog, this is ridiculous and unprofessional. Make a policy decision and stick to it, and dictate how alternative harnesses should work.

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#252

Post by NewsaHackO »

2001zhaozhao wrote: post #248

I think they're now charging it as extra usage if you use a custom prompt. In the Claude site they added the option to buy extra usage at 30% off if you buy $1,000 or more at a time, so it's still somewhat cheaper to use OpenClaw with a claude account compared to an API key. (Incidentally the 30% off might mean that choosing a Pro plan + extra usage versus Max plan might make sense for more people)

Yes, if it is "extra usage," then that just seems like an API with extra steps.

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#253

Post by mort96 »

giancarlostoro wrote: post #245
joshstrange wrote: post #192

Well that's clear as mud. I've complained, extensively, about this before but Anthropic really needs to make it clear what is and is not supported with or without a subscription. Until then, it's hard to know where you stand with using their products. I say all of this as someone who doesn't use OpenClaw or any Claw-like product currently. I just want to know what I can and can't do and currently it's impossible to k…

They really need to figure out the rules, look I'd love to use a custom harness with Claude Code that I can extend, or build my own (which I'm doing) and use it with my Claude Code license, I don't want to overspend on tokens if I can help it. They really need to set their bar for the next model releases to use less tokens, or to trim their own cost for how these models are run. I'd be okay with a slightly slower exp…

They might've just hit a ceiling with the quality they can get per token? Maybe the only real way left to scale quality is to increase token usage?

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#254

Post by ctxc »

giancarlostoro wrote: post #245
joshstrange wrote: post #192

Well that's clear as mud. I've complained, extensively, about this before but Anthropic really needs to make it clear what is and is not supported with or without a subscription. Until then, it's hard to know where you stand with using their products. I say all of this as someone who doesn't use OpenClaw or any Claw-like product currently. I just want to know what I can and can't do and currently it's impossible to k…

They really need to figure out the rules, look I'd love to use a custom harness with Claude Code that I can extend, or build my own (which I'm doing) and use it with my Claude Code license, I don't want to overspend on tokens if I can help it. They really need to set their bar for the next model releases to use less tokens, or to trim their own cost for how these models are run. I'd be okay with a slightly slower exp…

Out of curiosity, what kind of custom harness are you thinking?

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#255

Post by vegnus »

bandrami wrote: post #85
victorbjorklund wrote: post #43

Anthropic is really trying to burn all that goodwill they worked up by raising prices, reducing limits and making it impossible to know what the actual policies are.

If you want LLMs to continue to be offered we have to get to a point where the providers are taking in more money than they are spending hosting them. And we still aren't there (or even close).

I'll take local models over these corporate ones any day of the week. Hopefully it's only a matter of time

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#256

Post by GorbachevyChase »

joshstrange wrote: post #192

Well that's clear as mud. I've complained, extensively, about this before but Anthropic really needs to make it clear what is and is not supported with or without a subscription. Until then, it's hard to know where you stand with using their products. I say all of this as someone who doesn't use OpenClaw or any Claw-like product currently. I just want to know what I can and can't do and currently it's impossible to k…

Anthropic changing what you get for your subscription week to week is why I would never spend beyond a hobby-tier license. Great product. Probably. But maybe depending on what hours of the day you use it. If it suits them.

I can’t tell you how relieved I am that there are many capable open weight models in the wild to keep a ceiling on bad behavior.

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#257

Post by andai »

languagehacker wrote: post #197

My OpenClaw assistant (who's been using Claude) lost all his personality over the last week, and couldn't figure out how to do things he never had any issues doing. I racked up about $28 worth of usage and then it just stopped consuming anymore, so I don't know if there was some other issue, but it was persistent. I got sick of it and used a migration script to move my assistant's history and personality to a claude…

I thought the reason OpenClaw was banned because of the strain it's putting on the systems.

(Well, 3rd party stuff was already illegal, and I believe remains so (sorta-kinda tolerated now? with the extra usage[0]) but enforcement seemed to be based on excessive usage of subs.)

Doing the same thing but with 50K of irrelevant, proprietary system prompt, doesn't seem to improve the situation!

i.e. my question here is: if you replicate OpenClaw with `claude -p prooompt` and cron, is Anthropic happy? (Or perhaps their hope is that the people able and willing to do that represent a rounding error, which is probably true.)

[0] https://news.ycombinator.com/item?id=47633568

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#258

Post by andai »

Skidaddle wrote: post #244
languagehacker wrote: post #197

My OpenClaw assistant (who's been using Claude) lost all his personality over the last week, and couldn't figure out how to do things he never had any issues doing. I racked up about $28 worth of usage and then it just stopped consuming anymore, so I don't know if there was some other issue, but it was persistent. I got sick of it and used a migration script to move my assistant's history and personality to a claude…

What does your Claude Code implementation of OpenClaw look like?

Not who you asked but I slapped this together in 100 lines of code and you may find it useful. It's just `claude -p proompt` (or indeed, `codex exec prooompt` inside a Telegram bot. (Was annoyed by NanoClaw's claim that it was 500 lines, so tried my own hand at it ;)

No memory, no cron/heartbeat, context mgmt is just "new chat", but enough to get you started.

Note: no sandboxing etc, I run this as unprivileged linux user. So it can blow up its homedir, but not mine. Ideally, I'd run it on a separate machine. (My hottest take here is "give it root on a $3 VPS, reset if it blows up" ;)

https://github.com/a-n-d-a-i/ULTRON

You may also enjoy CLIProxyAPI, which does the same thing (claude -p / codex exec) but shoves a OpenAI compatible API around it. Note: this probably violates every AI company's ToS (since it turns the precious subsidized subscription tokens into a generic API). OpenAI seems to tolerate such violations, for now, because they care about good. Anthropic and Google do not.

(Though Anthropic may auto-detect and bill it as extra usage; see elsewhere in this thread. Situation is very confusing right now.)

https://github.com/router-for-me/CLIProxyAPI

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#259

Post by andai »

NewsaHackO wrote: post #252
2001zhaozhao wrote: post #248

I think they're now charging it as extra usage if you use a custom prompt. In the Claude site they added the option to buy extra usage at 30% off if you buy $1,000 or more at a time, so it's still somewhat cheaper to use OpenClaw with a claude account compared to an API key. (Incidentally the 30% off might mean that choosing a Pro plan + extra usage versus Max plan might make sense for more people)

Yes, if it is "extra usage," then that just seems like an API with extra steps.

Yeah I read it as a smart move. Good for PR, and it captures a bunch of value that was being lost. From what I understood, millions of users are making unauthorized usage of the subscription APIs. So they can just capture some of that money, some of them will stay and pay the extra usage. (Many of them aren't knowledgeable about API keys etc, they just used the auto setup in OpenClaw.)

The actual rules now are pretty confusing though. De jure illegal, de facto tolerated -- they'll just auto-detect and bill you for it.

The claude -p situation, though, confuses me. This one's technically legal but against the spirit of the law. (I think made illegal a few weeks ago since it was being used as a workaround for the OpenClaw ban, and seems to have been re-legalized now?)

But they can only extra-bill you for it if they can somehow detect it as invoked by OpenClaw, etc., right? If it's your own harness, it slips thru the cracks? ._.

Re: Anthropic says OpenClaw-style Claude CLI usage is allowed again

#260

Post by ex-aws-dude »

aurareturn wrote: post #126
freedomben wrote: post #115

Earlier quoted context omitted.

I feel this has to be said constantly, though I hate doing it. hn is not a monolith. People here routinely disagree with each other, and that's what makes it great

I'm aware. When I say "Hacker News", I mean a very sizable portion of users who keep repeating the OpenAI collapse imminent opinion.

https://en.wiktionary.org/wiki/Goomba_fallacy
Post reply on HN