Thanks for the writeup! What's an example of a general scientific reasoning agent? If you have a protocol for creating e.g. a strand of circular RNA, the agent searches through published protocols and understands variations, and then what does it do with the variations? Just tries them all?
I think the first very achievable thing is for an LLM to flesh out the details of a protocol. Perhaps the circular RNA protocol you're referencing doesn't list the exact buffer composition for one of the steps because they think it's obvious, but by analyzing other protocols it would be more possible to fill in those details.
"It works in my hands" is like "it works on my machine" in software
Thanks for the writeup! What's an example of a general scientific reasoning agent? If you have a protocol for creating e.g. a strand of circular RNA, the agent searches through published protocols and understands variations, and then what does it do with the variations? Just tries them all?
I think the first very achievable thing is for an LLM to flesh out the details of a protocol. Perhaps the circular RNA protocol you're referencing doesn't list the exact buffer composition for one of the steps because they think it's obvious, but by analyzing other protocols it would be more possible to fill in those details.
Makes sense