Why is OpenCode better than Claude Code?
Anthropic blocks third-party use of Claude Code subscriptions
251–260 of 533 posts
Re: Anthropic blocks third-party use of Claude Code subscriptions
#252This is an unusual L for Anthropic. The unfortunate truth is that the engineering in opencode is so far ahead of Claude Code. Obviously, CC is a great tool, but that's more about the magic of the model than the engineering of the CLI. The opencode team[^1][^2] built an entire custom TUI backend that supports a good subset of HTML/CSS and the TypeScript ecosystem (i.e. not tied to Opencode, a generic TUI renderer). Th…
Not unusual, not for Anthropic.
Re: Anthropic blocks third-party use of Claude Code subscriptions
#253Of course, they are banning for financial economic interests, not nominal alleged contractual violations, so Anthropic is not sympathetic.
// NOT LEGAL ADVICE
Obviously, I think it can make sense to Anthropic since opencode users likely disproportionately cost them money with little lock-in - you can switch the moment a comparable model is available elsewhere. It does not (necessarily) mean there are any legal or ethical issues barring us from continuously using the built-in opencode OAuth though.
Re: Anthropic blocks third-party use of Claude Code subscriptions
#254For 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…
Re: Anthropic blocks third-party use of Claude Code subscriptions
#255Anthropic should buy OpenCode and merge with CC
Re: Anthropic blocks third-party use of Claude Code subscriptions
#256For 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…
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.
Re: Anthropic blocks third-party use of Claude Code subscriptions
#257Genuine question, as someone who never used Claude Code, but used OpenCode/Aider/GeminiCli - as many here say Opencode is better, mind sharing why (from end user perspective)? I was thinking to try Claude Code later and may reconsider doing so.
I experimented with Claude Code but returned to the familiar Aider which existed before all of these tools AFAIK. You’ll notice people in Aider GitHub issues being concerned about its rather conservative pace of change, lack of plug-in ecosystem. But I actually started to appreciate these constraints as a way to really familiarise myself with the core “edit files in a loop with an end goal” that is the essence of all…
Opencode is totally different beast comparing to Aider and I mostly stopped using Aider for 2 months or so - it just iterate simpler and faster with OpenCode for me.
Re: Anthropic blocks third-party use of Claude Code subscriptions
#258Earlier quoted context omitted.
Not true, most tools are deterministic. For instance my programming language LSP just works 100% of the time with no failure. It doesn’t hallucinate any types, methods or variables.
Your LSP also can’t do complex reasoning across the purpose of your whole codebase.
Reasoning is an human trait.
Re: Anthropic blocks third-party use of Claude Code subscriptions
#259Re: Anthropic blocks third-party use of Claude Code subscriptions
#260Earlier quoted context omitted.
Every prompt is a run of probability - It’s at the core of the technology to be unable to give reproducible responses and even after a while, Claude is just as likely to sneak-in crimes in every snippet it outputs.
like the other commenter said. you need to learn to use new tools. and your take clearly indicates you haven't.