Every thread, in order.

One careful issue a week, no filter. Filter by thread or search for the one you half-remember.

Mar 16, 2026

“Just retry” only works if your operation is idempotent

Mar 9, 2026

128K tokens doesn’t mean you should use 128K tokens

Mar 2, 2026

Wrong timeout settings cause more outages than bugs

Feb 23, 2026

Your LLM application will hit rate limits. Here's how to handle it gracefully with exponential backoff, token buckets, and priority queuing.