391–400 of 533 posts
Funnily enough, I didn't know about opencode and will now test it out and likely use it instead. Improve your client so people prefer it? Nah. Try to force people to use your client by subsidizing it? Now that's what I'm talking about. As others said, why not just run a bunch of agents on Claude Code to surpass Opencode? I'm sure that's easy with their unlimited tokens!
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…
Earlier quoted context omitted.
Anthropic want you to use claude code cli badly and are prepared to be very generous if you do. People want to take that generosity without the reciprocity. I don't normally like to come down on the side of the megabigcorp but in this case anthropic aren't being evil. Not yet anyway.
I think they are. The key question is about why they want to you to use the CLI. If you're not the customer, you're the product. There's also a monopolistic aspect to this. Having the best model isn't something over can legally exploit to gain advantage in adjacent markets. It reeks of "Windows isn't done until Lotus won't run," Windows showing spurious error messages for DR-DOS, and Borland C++ losing to the then-in…
You are the customer, you're paying them directly.
The battle is for the harness layer. And it's quickly going the commodity way as well.
What's left for boutique-style AI companies?
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…
They definitely want their absolutely proprietary software with sudo privilege on your machine. I wonder why they would want that geeez
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…
They are subsidizing Claude code so they can use your data to train better coding models. You’re paying them to show their models how to code better.
Earlier quoted context omitted.
It is not unlimited, being not careful with your context management, you hit the limits quickly.
Isn't the context window the same for all plans, 200k? You would hit usage limits?
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…
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.
I can easily churn through $100 in an 8 hour work day with API billing. $200/month seems like an incredibly good deal, even if they apply some throttling.
Earlier quoted context omitted.
They are subsidizing Claude code so they can use your data to train better coding models. You’re paying them to show their models how to code better.
If true I wonder what kind of feedback loop is happening by training on human behavior that's directly influenced by the output of the same model
That data is critical to improve tool call use (both in correctness but also to improve when the agent chooses to use that tool). It's also important for the context rewrites Claude does. They rewrite your prompt and continuously manage the back-and-forth with the model. So does Cortex, just more aggressively with a more powerful context graph.
OpenCode brought this on themselves and their users. Plugging Claude Max subscriptions into other agents has been against the terms of service basically since the start and I imagine Anthropic must have issued plenty of warnings here that were ignored. They wouldn’t do this unless they really had to. If folks are mad about being rugged, blame OpenCode for misleading their users when they’ve long known this day was co…
That's a lot of supposition leading to a shaky conclusion. Your speculation may be correct, of course, but I have yet to see any mention of Anthropic issuing "plenty of warnings", or only taking this action because they "really had to."