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

Anthropic officially bans using subscription auth for third party use

code.claude.com

Post reply on HN
Print view View original

661–670 of 827 posts

Re: Anthropic officially bans using subscription auth for third party use

#661

Post by empath75 »

CuriouslyC wrote: post #576
bluelightning2k wrote: post #559

Reading these comments aren't we missing the obvious? Claude Code is a lock in, where Anthropic takes all the value. If the frontend and API are decoupled, they are one benchmark away from losing half their users. Some other motivations: they want to capture the value. Even if it's unprofitable they can expect it to become vastly profitable as inference cost drops, efficiency improves, competitors die out etc. Or wor…

Anthropic is going to be on the losing side with this. Models are too fungible, it's really about vibes, and Claude Code is far too fat and opinionated. Ironically, they're holding back innovation, and it's burning the loyalty the model team is earning.

I think you have it exactly backwards, and that "owning the stack" is going to be important. Yes the harness is important, yes the model is important, but developing the harness and model together is going to pay huge dividends.

Re: Anthropic officially bans using subscription auth for third party use

#662

Post by lucasyvas »

Isn’t this flawed anyway? If an application communicates with Claude Code over ACP (like Zed), it works fine?

Instead of using SDKs, this will just shift the third party clients to use ACP to get around it - Claude Code is still under the hood but you’re using a different interface.

This all seems pretty idiotic on their part - I know why they’re trying it but it won’t work. There will always be someone working around it.

Re: Anthropic officially bans using subscription auth for third party use

#663

Post by ac29 »

dgdosen wrote: post #633

Is it me, or will this just speed up the timeline where a 'good enough' open model (Qwen? Deepseek? - I'm sure the Chinese will see a value in undermining OpenAI/Anthropic/Google) combined with good enough/cheap hardware (10x inference improvement in a M7 Macbook Air?) makes running something like opencode code locally a no brainer?

The good enough alternative models are here or will be soon, depending on your definition of good enough. MiniMax-M2.5 looks really competitive and its a tenth of the cost of Sonnet-4.6 (they also have subscriptions).

Running locally is going to require a lot of memory, compute, and energy for the foreseeable future which makes it really hard to compete with ~$20/mo subscriptions.

Re: Anthropic officially bans using subscription auth for third party use

#664

Post by mccoyb »

butlike wrote: post #653
mccoyb wrote: post #645

Earlier quoted context omitted.

The opposite is true. There is barely any magic in the harness, the magic is in the model. Try it: write your own harness with (bash, read, write, edit) ... it's trivial to get a 99% version of (pick your favorite harness) -- minus the bells and whistles. The "magic of the harness" comes from the fun auxiliary orchestration stuff - hard engineering for sure! - but seriously, the model is the key item.

Not all percentages are weighted equally. That 1% is worth a lot more than the low-hanging 99% from your example

Is it? Look at pi, for instance.

It turns out that "most of the bell and whistles" could amount to instructing models how to use tools like tmux

Re: Anthropic officially bans using subscription auth for third party use

#665

Post by mccoyb »

tvink wrote: post #658
mccoyb wrote: post #645

Earlier quoted context omitted.

The opposite is true. There is barely any magic in the harness, the magic is in the model. Try it: write your own harness with (bash, read, write, edit) ... it's trivial to get a 99% version of (pick your favorite harness) -- minus the bells and whistles. The "magic of the harness" comes from the fun auxiliary orchestration stuff - hard engineering for sure! - but seriously, the model is the key item.

This is the complete opposite of my experience.

Does your experience include writing your own agent? Send a link

Re: Anthropic officially bans using subscription auth for third party use

#666

Post by JimmaDaRustla »

bluegatty wrote: post #152
JimmaDaRustla wrote: post #111

Earlier quoted context omitted.

Disingenuous analogy. It's more buying a season pass for Disneyland, then getting told you can't park for free if you're entering the park even though free parking is included with the pass. Still not unreasonable, but brings to light the intention of the tool is to force the user into an ecosystem rather.

It's not a disingenuous analogy ... whatever it is. But 'you can't park even though the ticket includes parking' is not an appropriate analogy because 3rd party use is definitely not intended. They did not 'state one thing' and the 'disallow it'. This is a pretty straight forward case of people using their subscription for 'adjacent' use, and Anthropic being more explicit about it. There's nothing fancy going on here…

Disingenuous or not, it was a bad analogy because it inferred that it was intentionally being abused which is completely false. The proof of that is this original post - Anthropic did not clearly (or even at all) identify how you could use your tokens with the subscription regardless of their intentions.

You're now misinterpreting my argument and misrepresenting it. I did not, in any way, suggest that Anthropic was "pulling the rug" to its users nor that they were entitled to use their tokens using the API with third parties. Full stop.

Of course, third-party API usage wasn't intended to be allowed for consuming subscription tokens. This is exactly what my analogy was structured to explain; a Disneyland season pass isn't intended to be used solely for parking. Anthropic did not intend for subscription tokens to be consumed by third-parties the same way users did not intend to abuse the subscription to derive more value than what was allotted to them. Your analogy missed that last part, which is absolutely crucial to understand.

I don't understand how you're making the exact arguments I'm making, then somehow completely misunderstanding what's being said.

Re: Anthropic officially bans using subscription auth for third party use

#667

Post by thepasch »

mccoyb wrote: post #641
bluelightning2k wrote: post #559

Reading these comments aren't we missing the obvious? Claude Code is a lock in, where Anthropic takes all the value. If the frontend and API are decoupled, they are one benchmark away from losing half their users. Some other motivations: they want to capture the value. Even if it's unprofitable they can expect it to become vastly profitable as inference cost drops, efficiency improves, competitors die out etc. Or wor…

"Training the specific harness" is marginal -- it's obvious if you've used anything else. pi with Claude is as good as (even better! given the obvious care to context management in pi) as Claude Code with Claude. This whole game is a bizarre battle. In the future, many companies will have slightly different secret RL sauces. I'd want to use Gemini for documentation, Claude for design, Codex for planning, yada yada ..…

> pi with Claude is as good as (even better! given the obvious care to context management in pi) as Claude Code with Claude

And that’s out of the box. With how comically extensible pi is and how much control it gives you over every aspect of the pipeline, as soon as you start building extensions for your own, personal workflow, Claude Code legimitely feels like a trash app in comparison.

I don’t care what Anthropic does - I’ll keep using pi. If they think they need to ban me for that, then, oh well. I’ll just continue to keep using pi. Just no longer with Claude models.

Re: Anthropic officially bans using subscription auth for third party use

#668

Post by SkyPuncher »

SkyPuncher wrote: post #572
cactusplant7374 wrote: post #475

Earlier quoted context omitted.

No developer writes the same prompt twice. How can you be sure something has changed?

When I use Claude daily (both professionally and personally with a Max subscription), there are things that it does differently between 4.5 and 4.6. It's hard to point to any single conversation, but in aggregate I'm finding that certain tasks don't go as smoothly as they used to. In my view, Opus 4.6 is a lot better at long standing conversations (which has value), but does worse with critical details within smaller…

Just hit a situation where 4.6 is driving me crazy.

I'm working through a refactor and I explicitly told it to use a block (as in Ruby Blocks) and it completely overlooked that. Totally missed it as something I asked it to do.

Re: Anthropic officially bans using subscription auth for third party use

#669

Post by thepasch »

andreagrandi wrote: post #273

I'm only waiting for OpenAI to provide an equivalet ~100 USD subscription to entirely ditch Claude. Opus has gone down the hill continously in the last week (and before you start flooding with replies, I've been testing opus/codex in parallel for the last week, I've plenty of examples of Claude going off track, then apologising, then saying "now it's all fixed!" and then only fixing part of it, when codex nailed at t…

> I’m only waiting for OpenAI to provide an equivalet ~100 USD subscription to entirely ditch Claude.

I have a feeling Anthropic might be in for an extremely rude awakening when that happens, and I don’t think it’s a matter of “if” anymore.

Re: Anthropic officially bans using subscription auth for third party use

#670

Post by ted537 »

mccoyb wrote: post #645
herzigma wrote: post #640

Earlier quoted context omitted.

More than just the real value: the real intelligence is in the harness.

The opposite is true. There is barely any magic in the harness, the magic is in the model. Try it: write your own harness with (bash, read, write, edit) ... it's trivial to get a 99% version of (pick your favorite harness) -- minus the bells and whistles. The "magic of the harness" comes from the fun auxiliary orchestration stuff - hard engineering for sure! - but seriously, the model is the key item.

Yeah I agree with this. The only tool that really matters is file patching -- which you can check something like the opencode patch implementation, its fairly straightforward.
Post reply on HN