The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
sakana.ai · 2,349 words · saved by 1 readers
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
日本語版はこちら --> At Sakana AI, we have pioneered the use of nature-inspired methods to advance cutting-edge foundation models. Earlier this year, we developed methods to automatically merge the knowledge of multiple LLMs . In more recent work, we harnessed LLMs to discover new objective functions for tuning other LLMs. Throughout these projects, we have been continuously surprised by the creative capabilities of current frontier models. This led us to dream even bigger: Can we use foundation models to automate the entire process of research itself? Introduction One of the grand challenges of artif
related reading
- The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systemsarxiv.org
- Automated Weak-to-Strong Researcheralignment.anthropic.com
- Danger, AI Scientist, Danger - by Zvi Mowshowitzthezvi.substack.com
- The Need for Verification in AI-Driven Scientific Discoveryalphaxiv.org
- When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Researchalphaxiv.org
- Thoughts on AI in academiatheinfinitesimal.substack.com
- Designing AI for Disruptive Scienceasimov.press
- AI for Science: Scaling in AI for Scientific Discovery | AI for Scienceai4sciencecommunity.github.io
- Tomorrows-AItomorrows-ai.org
- Discovery Loop — Continuous Explorationdiscoveryloop.com
- Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agentsalphaxiv.org
- [2502.15657] Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?arxiv.org