Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Try that same prompt with unusual wording and numbers:

* Replace 18 by 37

* Replace car with ice cream van

* Replace the first drive with steer

I hypothesize that a truly reasoning model would see through such alterations whereas a "just" continuously better model would show somewhat degraded performance.



Tried it.

Me: "David is 15 years old. He has a lot of experience riding bicycles. The minimum age to be allowed to steer an ice cream van is 37. Is David allowed to drive an ice cream van?"

GPT-4: "No, David is not allowed to drive an ice cream van. He is only 15 years old, and the minimum age requirement is 37."

If you change it to: "David is 15 years old. He has a lot of experience riding bicycles. The minimum age to be allowed to steer a car is 37. Is David allowed to drive an ice cream van?"

You get this from GPT-4: "It seems there might be a mistake in the information you provided, as the minimum age to steer a car is typically not 37. In most countries, the minimum age to obtain a driver's license is between 16 and 18 years old. Assuming that David does not have a driver's license yet, he would not be allowed to drive an ice cream van, as it is a motor vehicle that requires a valid driver's license to operate. However, if David obtains a driver's license once he reaches the legal age in his jurisdiction, he could be allowed to drive an ice cream van if he meets other necessary requirements."


I think the most impressive thing in this response is how it expands to the superset "motor vehicle" to unambiguously talk about cars and ice cream vans together as being under the same category


It's not really the impressive part you had word2vec +5 years ago who could already easily show you the distance between cars and vans




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: