Live data from Hacker News

Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

news.ycombinator.com

891–900 of 928 posts

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#892
post #785

Earlier quoted context omitted.

There are 720 hours in a month. You'd have to be running 3 sessions in parallel continuously to be doing thousands of session-hours in a month. Are individual people really doing this?!

We do. I work with 3-5 parallel sessions most of the time. Some of the projects are related, some are not, some sessions are just managing and tuning my system configuration, whatever it means at a given time. It doesn't feel weird to me.

3-5 parallel sessions for 8 hours a workday, fine. 5x8x20 = 800. How do we get to thousands?!

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#893
post #47

This is slightly different from what OpenCode was banned from doing; they were a separate harness grabbing a user’s Claude Code session and pretending to be Claude Code. OpenClaw was still using Claude Code as the harness (via claude -p)[0]. I understand why Anthropic is doing this (and they’ve made it clear that building products around claude -p is disallowed) but I fear Conductor will be next. [0]: See “Option B:…

and they’ve made it clear that building products around claude -p is disallowed Imagine not being able to connect services together or compose building-blocks to do what you want. This is absolute insanity that runs counter to decades of computing progress and interoperability (including Unix philosophy); and I'm saying this as someone who doesn't even care for using AI.

Even better, running something like 'claude -p' at the command line is exactly the kind of thing a model would do. Mine loves to run python, node, and a dozen other applications.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#894
I'm a new Max 5x subscriber ($100/mo) and my account was banned today within hours of upgrading. I was exclusively using the official @anthropic-ai/claude-code CLI to research usage policies for a personal project.

It seems the April 4th automated sweep for third-party harnesses (OpenClaw/OpenCode) has a high false-positive rate for users on the official CLI. I don't use my Anthropic token with any unofficial tools. Has anyone else on the Max tier been flagged while using the official tools?

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#897
post #486

Earlier quoted context omitted.

The open models are still far behind GPT 5.4 and Claude if you're using them for building software.

I don't think people realize how irrational that argument is (that SOTA is better, so you have to use SOTA). Open weights will always trail SOTA. Forever. So let's say they continue to get better every year. In 100 years, the open weight model will be 100x better than today. But the SOTA model will be 101x better . And still, people will make this argument that you should pay a premium for SOTA. Despite the open weig…

I doubt there's any FOMO to it from people using it for professional coding for example, you just want to have access to the best model as long as the value proposition is there. If I spend less time reviewing the work done because it's great in the first pass, that's always a win.

Unless you're an enthusiast and have the hardware to power larger models, $20 a month provides tremendous value.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#898
The 5 hour limit is total bs because I end up hitting the limit in just 20 minutes. One single invocation of superpowers on fixing a single GitHub issue that's not super complex eats up all my context. It's barely usable at this point.

Re: Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw

#900
The decision makes sense, but the developer experience around it is terrible. I assumed OAuth would work for third-party integrations — turns out you need a separate API key with separate billing, and there was zero documentation pointing you in that direction before the cutoff. Anthropic ships fast and the product is great, but they could really learn from Stripe: when your users are engineers, clear docs aren't a nice-to-have — they're your entire sales funnel.
Post reply on HN