Will replies to ten well-engineered GPT-4 prompts in my area of expertise outperform my own answers to them?
Example of what I mean by a well-engineered prompt:
"The following is an excerpt from the 'Guyton & Hall' authoritative textbook on human physiology. It describes the respective roles of RAAS, ANP, and ADH in controlling plasma osmolality and free water clearance through their effects on renal tubular transport."
Currently, I find ChatGPT's and GPT3's answers to questions of this complexity to sound convincing. However, when examined more closely they turn out to be factually wrong and inconsistent often enough to be useless.
Resolution based on the best judgment of a friend of mine who has tech expertise yet enough understanding of biomed sciences to be able to competently judge. (I was convinced that I might be biased, so I changed this from me resolving it based on my own best judgment.)
Since I will base my future use of GPT for study purposes on its performance relative to myself, I am incentivized to judge as truthfully as possible.
Dec 13, 8:08pm: Will replies to ten well-engineered prompts to GPT-4 in my area of expertise outperform my own answers to them? → Will replies to ten well-engineered GPT-4 prompts in my area of expertise outperform my own answers to them?
Close date updated to 2023-07-31 11:59 pm
I think technically by the rules it may have been too long but I can't remember exactly what the rules said at the time I posted that.
I think in any case it won't reopen for trading, and you also probably need to use whatever version of this model was available at around the time the question was active?
I see two options:
Either you do the game under the original rules and tell the result here, and I re-resolve it to that result
Or, you just make a new market with a similar question and run it yourself
@IsaacKing see prompt, it is stuff that is well known, can be found online but highly specific and involves integrating understanding of several complicated mechanisms