๐Ÿงฌ DiscoPOP/LLMยฒ Paper Is Out ๐Ÿฆพ


Stoked to share that our Sakana.AI paper on leveraging LLMs to discover better preference optimization algorithms is now available on arXiv ๐Ÿ“! We explore the capabilities of LLMs for automated scientific discovery. This was an outstanding collaboration with Cambridge and Oxford University! LLMs will completely revolutinize the scientific process ๐Ÿš€

๐Ÿ”– Paper: here. ๐Ÿ’ป Code: here. ๐Ÿ•ธ Blog: here. ๐Ÿฅ Twitter: here.