-23
How in the hell is this possible?
(slrpnk.net)
This is a most excellent place for technology news and articles.
I just fired up Llama2-70B, the biggest model I happen to have handy on my local machine, and repeated your exact prompt to it four times. The answers it gave were:
So one correct guess out of four attempts. Not a great showing. So I tried a more prompt-engineerish approach and asked it:
And gave it another four attempts. Its responses were:
Response 1:
Response 2:
Response 3:
Response 4:
So that was kind of interesting. It didn't get any more accurate - still just one "success" out of four - but by rambling on about its reasoning I think we can see how this particular model is getting tripped up and ending up at four so often. It's correctly realizing that it needs to double the number of horns, but it's mistakenly doubling it twice. Perhaps mixtral-8x7b is going down a similar erroneous route. Try asking it to explain its reasoning step by step.