| ▲ | politelemon 12 hours ago |
| Why were third party harnesses banned? Surely they'd want sticking power over the ecosystem. |
|
| ▲ | lelanthran 3 hours ago | parent | next [-] |
| > Why were third party harnesses banned? Surely they'd want sticking power over the ecosystem. Third-party harnesses are the exact opposite of stickiness! Ditching Claude Code for a third party harness while using the Claude Code subscription means it's trivial to switch to a different model when you {run out of credits | find a cheaper token provider | find a better model}. |
|
| ▲ | cedws 12 hours ago | parent | prev | next [-] |
| There’s the argument that Anthropic has built Claude Code to use the models efficiently, which the subscription pricing is based on. Maybe there’s some truth to that, but then why haven’t OpenAI made the same move? I believe the main reason is platform control. Anthropic can’t survive as a pipeline for tokens, they need to build and control a platform, which means aggressively locking out everybody else building a platform. |
| |
| ▲ | Zetaphor 11 hours ago | parent | next [-] | | Alternatively products like openclaw have an outsized impact on Anthropic's infrastructure for essentially no benefit to them. Especially when you're taking advantage of the $200 plan. OpenAI has never shyed away from burning mountains of cash to try and capture a little more market share. They paid a billion dollars for a vibe coded mess just for the opportunity to associate themselves with the hype. | | |
| ▲ | plusplusungood 6 hours ago | parent | next [-] | | > Taking advantage of the $200 plan. No, I'm paying $200 a month for a premium product that I expect premium service for. It's the single most expensive IT expense I have. Taking advantage my foot. | | |
| ▲ | 59nadir 2 hours ago | parent | next [-] | | Can you imagine paying the actual cost of it, or a subscription cost that at least ballpark matched it? I don't think I have a single friend or acquaintance who realistically would. | |
| ▲ | infecto 4 hours ago | parent | prev | next [-] | | You are simply a bit too entitled. It's not a premium product and honestly not that expensive in my opinion either (though that is going to depend on your location). You are more than able to pay for API rates. | |
| ▲ | charcircuit 5 hours ago | parent | prev [-] | | It's not a premium product. It's just expensive. |
| |
| ▲ | qeternity 4 hours ago | parent | prev [-] | | > They paid a billion dollars for a vibe coded mess just for the opportunity to associate themselves with the hype. Lol no they didn't. It wasn't even an acquihire. They just hired Peter. Maybe they are paying him incredibly well, but not a billion dollars well. |
| |
| ▲ | snovv_crash 2 hours ago | parent | prev [-] | | I think it's a training data thing. They can only gather valid training data from real human interactions, so they don't want to subsidize tokens for purely automated interactions. |
|
|
| ▲ | klempner 9 hours ago | parent | prev | next [-] |
| Note that the thing that's banned is using third party harnesses with their subscription based pricing. If you're paying normal API prices they'll happily let you use whatever harness you want. |
|
| ▲ | sshine 9 hours ago | parent | prev | next [-] |
| One thing is lack of control of token efficiency on what’s already a subsidised product. Another thing is branding: Their CLI might be the best right now, but tech debt says it won’t continue to be for very long. By enforcing the CLI you enforce the brand value — you’re not just buying the engine. |
| |
|
| ▲ | visarga 4 hours ago | parent | prev | next [-] |
| I want to differentiate 2 kinds of harnesses 1. openclaw like - using the LLM endpoint on subscription billing, different prompts than claude code 2. using claude cli with -p, in headless mode The second runs through their code and prompts, just calls claude in non-interactive mode for subtasks. I feel especially put off by restricting the second kind. I need it to run judge agents to review plans and code. |
|
| ▲ | brookst 9 hours ago | parent | prev [-] |
| To be clear they weren’t banned from Claude usage, they were required to use the API and API rates rather than Claude Max tokens. Claude code uses a bunch if best practices to maximize cache hit rate. Third party harnesses are hit or miss, so often use a lot more tokens for the same task. |
| |
| ▲ | ledauphin 9 hours ago | parent | next [-] | | nah this doesn't explain it. most of the users of those third party harnesses care just as much about hitting cache and getting more usage. | | |
| ▲ | SyneRyder 8 hours ago | parent | next [-] | | I'm watching a conference talk right now from 2 weeks ago: "I Hated Every Coding Agent So I Built My Own - Mario Zechner (Pi)", and in the middle he directly references this. He demonstrates in the code that OpenCode aggressively trims context, by compacting on every turn, and pruning all tool calls from the context that occurred more than 40,000 tokens ago. Seems like it could be a good strategy to squeeze more out of the context window - but by editing the oldest context, it breaks the prompt cache for the entire conversation. There is effectively no caching happening at all. https://youtu.be/Dli5slNaJu0 | |
| ▲ | brookst 2 hours ago | parent | prev [-] | | Sure. The question is whether they have the same level of expertise and prioritization that Anthropic does. |
| |
| ▲ | lacunary 9 hours ago | parent | prev [-] | | but claude -p is still Claude Code | | |
| ▲ | danmaz74 9 hours ago | parent [-] | | Was something using that been banned? | | |
| ▲ | SyneRyder 8 hours ago | parent [-] | | Yep, that's the reason for the new Extra Credit feature in Claude Code. Some people were wiring up "Claude -p" with OpenClaw, so now Anthropic detects if the system prompt contains the phrase OpenClaw, and bills from Extra Credit if that happens: https://x.com/steipete/status/2040811558427648357 "Anthropic now blocks first-party harness use too claude -p --append-system-prompt 'A personal assistant running inside OpenClaw.' 'is clawd here?' → 400 Third-party apps now draw from your extra usage, not your plan limits. So yeah: bring your own coin " | | |
|
|
|
