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

Anthropic blocks third-party use of Claude Code subscriptions

github.com

Post reply on HN
Print view View original

371–380 of 533 posts

Re: Anthropic blocks third-party use of Claude Code subscriptions

#371

Post by giancarlostoro »

dfabulich wrote: post #112

For folks not following the drama: Anthropic's $200/month subscription for Claude Code is much cheaper than Anthropic's pay-as-you-go API. In a month of Claude Code, it's easy to use so many LLM tokens that it would have cost you more than $1,000 if you'd paid via the API. Why is Anthropic offering such favorable pricing to subscribers? I dunno. But they really want you to use the Claude Code™ CLI with that subscript…

> More importantly, Anthropic should have open sourced their Claude Code CLI a year ago. (They can and should just open source it now.)

It's not like if it houses some top secret AI models inside of it, and it would make way more sense, and probably expand the capabilities of Claude Code itself. Do they lose out to having OpenAI or other competitors basically stealing their approach?

Re: Anthropic blocks third-party use of Claude Code subscriptions

#373

Post by giancarlostoro »

danmaz74 wrote: post #300
dfabulich wrote: post #112

For folks not following the drama: Anthropic's $200/month subscription for Claude Code is much cheaper than Anthropic's pay-as-you-go API. In a month of Claude Code, it's easy to use so many LLM tokens that it would have cost you more than $1,000 if you'd paid via the API. Why is Anthropic offering such favorable pricing to subscribers? I dunno. But they really want you to use the Claude Code™ CLI with that subscript…

> More importantly, Anthropic should have open sourced their Claude Code CLI a year ago. (They can and should just open source it now.) "Should have" for what reason? I would be happy if they open sourced Claude Code, but the reality is that Claude Code is what makes Anthropic so relevant in the programming more, much more than the Claude models themselves. Asking them to give it away for free to their competitors se…

Yeah, I've heard of people swapping out the model that Claude Code calls and apparently its not THAT much of a difference. What I'd love to see from Anthropic instead is, give me smaller LLM models, I don't even care if they're "open source" or not, just pull down a model that takes maybe 4 or 6 GB of VRAM into my local box, and use those for your coding agents, you can direct it and guide it with Opus anyway, so why not cut down on costs for everyone (consumer and Anthropic themselves!) by just letting users who can run some of the compute locally. I've got about 16GB of VRAM I can juice out of my Macbook Pro, I'm okay running a few smaller models locally with the guiding hand of Opus or Sonnet for less compute on the API front.

Re: Anthropic blocks third-party use of Claude Code subscriptions

#375

Post by xpe »

isodev wrote: post #165
luckilydiscrete wrote: post #161

Earlier quoted context omitted.

I'll say "maybe-sometimes works" is a misunderstanding. It feels like that initially, but that's no different from any new tool you adopt. A jackhammer also "maybe-sometimes works" as a hammer replacement.

Every prompt is a run of probability - It’s at the core of the technology to be unable to give reproducible responses and even after a while, Claude is just as likely to sneak-in crimes in every snippet it outputs.

> Every prompt is a run of probability - It’s at the core of the technology to be unable to give reproducible responses and even after a while, Claude is just as likely to sneak-in crimes in every snippet it outputs.

Some readers might interpret "a run of probability" to mean "we can't say anything about the statistical distribution". I don't think the commenter means that, but still, communicating statistics is hard, so I suggest being careful.

For example, writing "even after a while, just as likely to sneak-in crimes in every snippet it outputs" is pretty attention-getting and even provoking. What does the commenter mean by it? What kind of 'crimes' do they mean? Does the commenter really mean 'just as likely'? Just as likely as what? I would think most readers would form very different takes.

Re: Anthropic blocks third-party use of Claude Code subscriptions

#377

Post by elfly »

sirtaj wrote: post #359
reactordev wrote: post #339

Earlier quoted context omitted.

Claude code is nothing more than a loop to Opus.

I use Q/aka kiro-cli at work with opus and it's clearly inferior to CC within the first 30s or so of usage. So no, not quite

Kiro is such a disaster. It starts well with all the planning, but I haven't been able to control it. It changes files on a whim and changes opinion from paragraph to paragraph.

Also it uses the Claude models but afaik it is constantly changing which one is using depending on the perceived difficulty.

Re: Anthropic blocks third-party use of Claude Code subscriptions

#378

Post by tacoooooooo »

giancarlostoro wrote: post #373
danmaz74 wrote: post #300

Earlier quoted context omitted.

> More importantly, Anthropic should have open sourced their Claude Code CLI a year ago. (They can and should just open source it now.) "Should have" for what reason? I would be happy if they open sourced Claude Code, but the reality is that Claude Code is what makes Anthropic so relevant in the programming more, much more than the Claude models themselves. Asking them to give it away for free to their competitors se…

Yeah, I've heard of people swapping out the model that Claude Code calls and apparently its not THAT much of a difference. What I'd love to see from Anthropic instead is, give me smaller LLM models, I don't even care if they're "open source" or not, just pull down a model that takes maybe 4 or 6 GB of VRAM into my local box, and use those for your coding agents, you can direct it and guide it with Opus anyway, so why…

not sure there are any models yet that you can get the quality out you need to do this and run on your mbp

Re: Anthropic blocks third-party use of Claude Code subscriptions

#379

Post by 12345hn6789 »

Majromax wrote: post #361
elAhmo wrote: post #263

Earlier quoted context omitted.

This take is ridiculous. Nearly everyone who uses Max agrees that what they get for the money paid is an amazing deal. If you don't use or understand how LLMs fit in your workflows, you are not the target customer. But for people who use it daily, it is a relatively small investment compared to the time saved.

> If you don't use or understand how LLMs fit in your workflows, you are not the target customer. I feel like this is a major area of divergence. The "vibes" are bifurcating between "coding agents are great!" and "coding agents are all hype!", with increasing levels of in-group communication. How should I, an agent-curious user, begin to unravel this mess if $200 is significantly more than pocket change? The pro-agen…

The$20 plan exists for a reason. If you're interested you can give it a whirl.

Re: Anthropic blocks third-party use of Claude Code subscriptions

#380

Post by kurtis_reed »

altmanaltman wrote: post #364
danmaz74 wrote: post #300

Earlier quoted context omitted.

> More importantly, Anthropic should have open sourced their Claude Code CLI a year ago. (They can and should just open source it now.) "Should have" for what reason? I would be happy if they open sourced Claude Code, but the reality is that Claude Code is what makes Anthropic so relevant in the programming more, much more than the Claude models themselves. Asking them to give it away for free to their competitors se…

> the reality is that Claude Code is what makes Anthropic so relevant in the programming more, much more than the Claude models themselves but Claude Code cannot run without Claude models? What do you mean?

https://github.com/musistudio/claude-code-router
Post reply on HN