How to tell if your AI agent actually got better
The agent's reply is not the result, LLM judges have blind spots of their own, and a few dozen real failures beat a thousand synthetic tests.
evals
Posts tagged evals on Valentin Shapovalov.
Posts tagged evals on Valentin Shapovalov.
The agent's reply is not the result, LLM judges have blind spots of their own, and a few dozen real failures beat a thousand synthetic tests.
Get new posts delivered to your inbox.