The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
In this article
- Sakana AI, has developed methods to automatically merge the knowledge of multiple LLMs. In more recent work, they harnessed LLMs to discover new objective functions for tuning other LLMs.
- Throughout these projects, they were continuously surprised by the creative capabilities of current frontier models.
- This led them to dream even bigger: Can we use foundation models to automate the entire process of research itself?
