draismaa Karma 1 Created 1 year ago Recent Submissions 1. ▲ Agent simulations = unit testing for AI? 2 points · 5 months ago · 2 comments 2. ▲ We hit a wall testing AI agents, agents simulations works better 2 points · 5 months ago · 1 comment 3. ▲ Evaluations are crucial, but what should you eval on? (github.com) 2 points · 9 months ago · 1 comment 4. ▲ Show HN: Experiment with DSPy optimzers, track performance of LLM-features (github.com) 2 points · 11 months ago · 2 comments All submissions on HN · View profile on HN