alt Hacker NewsInteresting but how is an "autoresearch loop" different than creating a spec and X number of testcases and letting an agent run against these testcases and the spec?
Interesting but how is an "autoresearch loop" different than creating a spec and X number of testcases and letting an agent run against these testcases and the spec?
Scoring would probably be the big difference because the outcome is to optimize performance or optimize a score or a metric versus just a pass fail.