We built a learning loop that learns from its own failures

Show HN: We built a learning loop that learns from its own failures

Operating in show hn launch, We built a learning loop that learns from its own failures operates.

Profile

We recently published our research on the learning loop behind the Dropstone agent. Instead of throwing more compute at a problem or trying to dynamically update weights, we tested what happens when you give a frozen open-weight model persistent memory of its own mistakes.We found that by keeping three stores the Experience, Lessons, and Knowledge the agent successfully builds up scar tissue. In a held-out study, it was able to independently rediscover hidden mathematical laws and coding rules purely from trial, error, and data.

Its activity falls under show hn launch; the profile below is assembled from public directory data.

Its current recorded stage is Show HN launch.

Website: blankline.org/research/intelligence-compounds