I read what’s new in AI at the source, then explain it with everyday life.
No article matches.
build-eval writes an exam for your AI app with you; hillclimb revises against it one change at a time, with held-out cases to catch cramming.
Sonnet 5.5 is 30% faster than Sonnet 5 at the same per-token price. Swapping the model name is easy; three habits in your code are not.
