This is false. We defaulted to medium as a result of user feedback about Claude using too many tokens. When we made the change, we (1) included it in the changelog and (2) showed a dialog when you opened Claude Code so you could choose to opt out. Literally nothing sneaky about
@bcherny
-
TypeScript Performance: Simplifying Build Without Native Dependencies
By
–
TS felt simpler if we could make it fast — no napi, no native builds, no per platform vendoring
-
Performance optimization strategies for file search systems
By
–
The wins came from three places: 1. Pre-computing upfront in a clever way that doesn't block the main thread
2. Avoiding NAPI overhead for small result sets
3. Iteratively asking Claude to find perf improvements for faster file search -
Claude Code v2.1.85 Faster Mentions Feature Released
By
–
Enjoy faster @-mentions in Claude Code! This went out in v2.1.85.
-
TypeScript Port Delivers 3x P99 Performance Improvement
By
–
After a few hours, I had a PR. The results were solid — P99 got 3x faster after porting to TypeScript!
-
Refining Abuse Detection Systems and Technical Terminology
By
–
We think this is an overactive abuse-detection system, digging in. Also working on making the terms for -p crystal clear.
-
Token efficiency improvements enable extended AI sessions
By
–
We've been landing token-efficiency improvements so you can do more in your sessions. If you have a session where usage felt particularly high, can you run /bug and post the feedback id? Feel free to tag me directly
-
Report AI Model Changes and Behavioral Issues
By
–
Hmm there were no behavioral/model changes recently. If you see something weird (eg. the model refusing to do something) mind running /bug and posting the feedback id? Feel free to tag me
-
Overactive AI abuse classifier requires policy clarification
By
–
This is not intentional, likely an overactive abuse classifier. Looking, and working on clarifying the policy going forward.