|
|
|
|
|
|
by wing-_-nuts
33 days ago
|
|
|
Personal experience? You ask it for the name of the paper referenced. You google that paper (for some reason it's not great at going out and acquiring the paper). You then upload the pdf and ask it if the paper supports the assertion if it's not quickly findable via ^F. You go read, ask it clarifying questions about hazard ratios, what they controlled for, etc. AI is quite good when grounded in a source. |
|
|