logoalt Hacker News

froh42today at 4:18 PM2 repliesview on HN

I was just curious asked chatgpt:

How can I make a really great steak myself? What to look out for, what to do. Give me detailed instructions.

I got a really good answer (including - cut, temperature and reverse searing), so I probably won't even need understanding. (Oh - and yes, I can cook - the answer mirrors what I already know).

Yes, it was a very, very poor analogy, because cooking a steak is a well known and well documented thing where LLMS produce good output. They fail when you get off the beaten path and try to do something that's not "mainstream".


Replies

_puktoday at 6:45 PM

I compare this to doing my first smoke (was gifted a smoker).

AI gave me the cut, the temp, the timing, the things to watch out for.

Chicken's the best to try first, can't mess that up.

After goodness knows how many hours..

Pretty inedible leathery chicken..

"Oh my bad! I gave you the timings for a different meat"

bluGilltoday at 4:40 PM

AI has proved several times they can prove some complex math things that humans have been trying for decades so solve. They have not failed and have clearly done complex things humans cannot. Since humans have not done it before you cannot call it on the beaten path.