This collection costed me around one-month Claude pro subscription around April/May I think. Staggered because of rate-limiting. But it was almost entirely developed on my phone, with Claude Code in the Claude app cloning the github repo, raising PRs, and Netlify giving me previews of the PR's changes for me to see before merging. So I used to have like 3/4 Claudes working on separate games, and review them in the PR previews, discard/approve as I see fit.
After that, once the original shape, architecture and philosiphy were set in, I now maintain it mostly with Opencode's free models (BigPickle and MiMo), or models from Kimi/Gemma/DeepSeek, via DeepInfra.
In all, so far it costed ~$30 may be. Totally worth it. :)
I'm taking this more as a "pricing" change. Like, if you pay 200$ then you can use inference only in these limited scopes. If you want more unrestricted access to inference, use the API token pricing.
Which, seems fine? They could've just not offered the 200$ plan and perhaps nobody would've complained. They tried it, noticed it being unsustainable, so they're trying to remodel it to it _is_ sustainable.
Hey Peter! It's so humbling to see you check out my blog!
Your articles on awk and sed were a huge inspiration to me around 2008-09, and I super-looked up to you. Never have I imagined you would check out my blog one day!
This collection costed me around one-month Claude pro subscription around April/May I think. Staggered because of rate-limiting. But it was almost entirely developed on my phone, with Claude Code in the Claude app cloning the github repo, raising PRs, and Netlify giving me previews of the PR's changes for me to see before merging. So I used to have like 3/4 Claudes working on separate games, and review them in the PR previews, discard/approve as I see fit.
After that, once the original shape, architecture and philosiphy were set in, I now maintain it mostly with Opencode's free models (BigPickle and MiMo), or models from Kimi/Gemma/DeepSeek, via DeepInfra.
In all, so far it costed ~$30 may be. Totally worth it. :)