Context windows are not memory
A million tokens of context does not give a model memory. It gives it a very large short-term working set — and confusing the two is why your agent forgets what it decided twenty minutes ago.
Article6 min
Write the eval first
Prompt engineering without an eval is just vibes with extra steps. Here's how to build a scoring harness in an afternoon, and why twenty examples beat two thousand.
Article6 min