Google Research has introduced WikiSkill, a framework that gives AI agents a persistent knowledge base. Instead of discarding what they learned after each run, agents document both failures and successes in a wiki-like structure and use that knowledge to get better over time. Larger models benefit more, but smaller models with WikiSkill can match the performance of larger ones without it.
The article Google's WikiSkill gives AI agents a persistent memory of past mistakes to sharpen future performance appeared first on The Decoder.
source & further reading
the-decoder.com — original article
LAION drops massive open video dataset with 10 million hours of footage for AI research
OpenAI cuts off Cursor after SpaceX acquisition, citing Musk's history of breaking contracts
Google Deepmind's AI Co-Scientist now plans experiments, runs lab equipment, and writes scientific papers