diff --git a/tips/assets/boris-10-mar-26/0.png b/tips/assets/boris-26-3-10/0.png similarity index 100% rename from tips/assets/boris-10-mar-26/0.png rename to tips/assets/boris-26-3-10/0.png diff --git a/tips/assets/boris-10-mar-26/1.png b/tips/assets/boris-26-3-10/1.png similarity index 100% rename from tips/assets/boris-10-mar-26/1.png rename to tips/assets/boris-26-3-10/1.png diff --git a/tips/claude-boris-2-tips-10-mar-26.md b/tips/claude-boris-2-tips-10-mar-26.md index 93e7516..77b1846 100644 --- a/tips/claude-boris-2-tips-10-mar-26.md +++ b/tips/claude-boris-2-tips-10-mar-26.md @@ -19,7 +19,7 @@ New in Claude Code: **Code Review**. A team of agents runs a deep review on ever - Boris has been using it for a few weeks and found it catches many real bugs he would not have noticed otherwise - When a PR opens, Claude dispatches a team of agents to hunt for bugs -Boris Cherny announcing Code Review +Boris Cherny announcing Code Review --- @@ -31,7 +31,7 @@ Roughly, the more tokens you throw at a coding problem, the better the result. B - Similar to engineering teams: if Boris causes a bug, his coworker reviewing the code might find it more reliably than he can - In the limit, agents will probably write perfect bug-free code — until then, **multiple uncorrelated context windows** tends to be a good approach -Boris Cherny on test time compute +Boris Cherny on test time compute ---