Why would they use their most expensive model when sonnet or opus can do the job as well?
Anthropic is also doing this for long context >= 200k Tokens on Sonnet 4.5
It hard resets limits every 5 hours instead of a sliding window?
Since last week it’s possible to use Claude Code in the VSCode terminal where it now automatically installs a plugin to display the diffs.
Prompt preprocessing is heavily compute-bound, so relying significantly on processing capabilities. Bandwidth mostly affects token generation speed.
You should check out out MCP by Anthropic, which solves some of the issues you mentioned.
Wait until you find out that the company behind it was doing a crypto scam before they worked on the new AI hype