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

421–430 of 533 posts

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

#421

Post by cobolcomesback »

elfly wrote: post #377
sirtaj wrote: post #359

Earlier quoted context omitted.

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.

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

Claude Code does the same. You can disable it in Kiro by specifically setting the model to what you want rather than “auto” using /model.

Tbh I’ve found Kiro to be much better than Claude Code. The actual quality of results seems about the same, but I’ve had multiple instances where Claude Code get stuck because of errors making tool calls whereas Kiro just works. Personally I also just prefer the simplicity of Kiro’s UX over CC’s relative “flashy” TUI.

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

#422

Post by eli »

grumbelbart2 wrote: post #220
eli wrote: post #139

Earlier quoted context omitted.

I couldn't. Aside from violating laws in various countries and opening them up to lawsuits, it would be extremely bad for their enterprise business if they were caught stealing user data.

Maybe. But the data is there, imagine financial troubles, someone buys in and uses the data for whatever they want. Much like 23andme. If you want something to stay a secret, you don't send it to that LLM, or you use a zero-retention contract.

If your threat model is "vendor willing to ignore contracts and laws to steal your data" I can't see how a zero-retention contract helps.

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

#423

Post by samrolken »

jbstack wrote: post #265
moltar wrote: post #254

Earlier quoted context omitted.

To extend your all you can eat analogy. It’s similar to how all you can eat restaurants allow you to eat all you can within the bounds of the restaurant, but you aren’t allowed to bring the food out with you.

It's not really a fair analogy. Restaurants don't want you taking food away because they want to limit the amount you eat to a single meal, knowing that you'll stop when you get full. If you take food out you can eat more by waiting until the next meal when you're hungry again. You don't "get full" and "get hungry again" by switching UIs. You can consume the same amount whether you switch or you don't switch.

Claude Code does a lot of work in optimizing context usage, how much output is included by tools and how that's done, and when to compact. This very well may make the cost of providing the subscription lower to Anthropic when Claude Code is used. It's well within the realm of possibility if not likelihood that other tools don't have the same incentive to optimize the buffet usage.

Not sure where that goes in the analogies here but maybe something about smaller plates.

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

#424

Post by samrolken »

dfabulich wrote: post #266
moltar wrote: post #254

Earlier quoted context omitted.

To extend your all you can eat analogy. It’s similar to how all you can eat restaurants allow you to eat all you can within the bounds of the restaurant, but you aren’t allowed to bring the food out with you.

Not really. At a buffet restaurant, if you could take the food out with you, you'd takeaway more food than you can eat at one sitting. OpenCode users and Claud Code™ CLI users use tokens at approximately the same rate. This is more like an all-you-can-eat restaurant requiring you to eat with their flimsy plastic forks, forbidding you to bring your own utensils.

Claude Code does a lot regarding optimizing context usage, tool output, sub-agent interactions, context compaction, and stuff like that. I don't imagine OpenCode has the same financial incentive to decrease the token cost Anthropic takes on under the subscriptions.

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

#425

Post by kachapopopow »

as much as I love opus I hate this company (not for the reasons you'd think thought). I just have a proxy that exposes an unauthenticated endpoint and bypasses all their attempts at banning for opencode usage since I was already on like my 5th claude account trying to get around random bans.

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

#427

Post by Izkata »

schiem wrote: post #382
muppetman wrote: post #148

I feel like I'm the only person on this site that doesn't use AI for coding. I guess there's probably a lot of other people that haven't commented on this story who don't use it either. But when I read about how much hype and all that sort of stuff there is in the AI industry, and then I see the amount of posts and commentary and deep technical discussion about how this feature has affected people, I'm not so sure. E…

I don't use it at all for a variety of reasons, but I rarely bother to get into discussions on HackerNews. Looking at how new it is, and how quickly things are changing, it seems likely that I could adopt it into my workflow in a month or two if it turns out that that's necessary. On the other hand, I've spent the last 2 decades building skills as a developer. I'm far more worried that becoming a glorified code revie…

> I'm far more worried that becoming a glorified code reviewer will atrophy those skills

A co-worker who went all-in around a year ago admitted a few months ago he's noticed this in himself, and was trying to stop using the code-generating functionality of any of these tools. Emphasis on "try": apparently the times it does work amazingly makes it addictive like gambling, and it's far too easy to reach for.

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

#428

Post by rovr138 »

ehnto wrote: post #316
_zoltan_ wrote: post #218

Earlier quoted context omitted.

you yourself admit that API access is a separate product. if you want to use 3rd party tooling, pay for API access. if you want to use (most likely heavily) subsidized subscription plans, use their ecosystem. it's that simple.

No one said it was complicated, and you might be imagining that I care more than I do. However if you can't understand why having a feature of a paid product removed is dissatisfying, then I cannot help you understand any further. I am surprised that anyone would think the "product" is the web interface and cli tool though, the product is very clearly the model. The difference in all options is merely how you access…

> having a feature of a paid product removed is dissatisfying

It wasn't a feature. It was a loophole. They closed it.

There are multiple products. Besides models, there's a desktop app, there's claude code. They have subscriptions.

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

#429

Post by dpark »

jbstack wrote: post #265
moltar wrote: post #254

Earlier quoted context omitted.

To extend your all you can eat analogy. It’s similar to how all you can eat restaurants allow you to eat all you can within the bounds of the restaurant, but you aren’t allowed to bring the food out with you.

It's not really a fair analogy. Restaurants don't want you taking food away because they want to limit the amount you eat to a single meal, knowing that you'll stop when you get full. If you take food out you can eat more by waiting until the next meal when you're hungry again. You don't "get full" and "get hungry again" by switching UIs. You can consume the same amount whether you switch or you don't switch.

> You don't "get full" and "get hungry again" by switching UIs. You can consume the same amount whether you switch or you don't switch.

This is actually a compelling argument for Claude Code getting the discount but not extending it to other cases. Claude Code, being subsidized by the company, is incentivized to minimize token usage. Third parties that piggyback on the same flat rate subscription, are not. i.e. Claude code wants you to eat less.

Of course, I don’t believe at all that this is why Anthropic has blocked this use case. But it is a reasonable argument.

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

#430

Post by dpark »

isolli wrote: post #228
casparvitch wrote: post #119

Earlier quoted context omitted.

I guess one issue is that you pay $200/month whether you use it or not. Potentially this could be better for Anthropic. What was not necessarily foreseeable (ok maybe it was) back when that started was that users have invented all kinds of ways to supervise their agents to be as efficient as possible. If they control the client, you can't do that.

Why is supervising one's agents to be as efficient as possible a problem for Anthropic?

When people say efficient here, they mean cost efficient, extracting as much work per dollar from Anthropic as possible. This is the opposite of Anthropic’s view of efficiency, which would be providing the minimal amount of service for the most amount of money.
Post reply on HN