With 1m context window, most users don’t need it anymore. If you miss it, ask claude to re-enable it in your settings.
@bcherny
-
Test Time Compute and Subagents: Optimizing AI Results
By
–
Roughly, the more tokens you throw at a coding problem, the better the result is. We call this test time compute. One way to make the result even better is to use separate context windows. This is what makes subagents work, and also why one agent can cause bugs and another
-
Model Effort Levels: Medium Balances Speed and Intelligence
By
–
Medium is a better default for most tasks. Think of effort as “max effort” — the model may decide to use less effort if it wants, and can use up to the amount of effort you set it to. It’s a balance- Low: fast and less intelligent
Medium: balanced
High: very intelligent, can be -
Reliability Improvements Expected in Recent AI Releases
By
–
Reliability is a hard problem and we take it very seriously. Things should be feeling better in more recent releases, and you should expect more improvements
-
Branch Protection Bypass: Pushing and Unpushing Code Security
By
–
If one can push to main without branch protections, one can also unpush
-
Claude Code Gets Customizable Spinner Verbs Feature
By
–
In the next version of Claude Code, you can customize spinner verbs for yourself and your team
-
Memory Leak Debug: Heap Dump Analysis Request
By
–
What memory leak? Can you take a heap dump and dm me?
-
Skills and slash commands are equivalent in AI tools
By
–
Yes! Skills and slash commands are the same thing