We can point to a handful of strange examples where GPT4 appears to be unsuccessful, but that ignores the buckets of examples where it knocks things out of the park.
And the areas where it isn't successful appear to being closed quickly as new discoveries are found - GPT4 is dramatically better at maths and truthiness than GPT3.5 for instance (still not perfect at either, but improved enough).
GPT4 can do things a child can't do, and a child can do things that GPT4 can't do. You don't have to be able to do everything a human can do to be classed as intelligent, and GPT currently underperforms humans in some areas and overperforms them in others.
Given a list of officials, absolutely, and if there is no list, nobody would just start spouting off names that don't match the rule at all -- and the failure here is due to inability to apply basic stated directions in a logical manner. Most likely this is due to the processing of tokens not being on a character level, but it will also imply that it possesses character-level language knowledge if you ask it to produce a list of infrequent trigrams in the English language:
> As an AI language model, I do not have access to a pre-existing list of the least frequent trigrams in English. However, I can generate a list of some of the rarest trigrams based on the frequency of occurrence in a large corpus of English language text. . . . (list follows)
How can I be sure of this list it claims to generate when I have evidence it can't identify substrings?
Inability to complete certain tasks does not mean that the system is not intelligent.
It’s possible for a system to be intelligent and also fail at these questions.
IMO a system is intelligent if it can answer some questions that require intelligence (by definition) - it does not have to be able to answer all questions.
I hadn’t heard of “truthiness” outside of Boolean comparisons in programming languages, but when I looked it up, it doesn’t seem like something worth aspiring to:
> Truthiness is the belief or assertion that a particular statement is true based on the intuition or perceptions of some individual or individuals, without regard to evidence, logic, intellectual examination, or facts. Truthiness can range from ignorant assertions of falsehoods to deliberate duplicity or propaganda intended to sway opinions.
And the areas where it isn't successful appear to being closed quickly as new discoveries are found - GPT4 is dramatically better at maths and truthiness than GPT3.5 for instance (still not perfect at either, but improved enough).
GPT4 can do things a child can't do, and a child can do things that GPT4 can't do. You don't have to be able to do everything a human can do to be classed as intelligent, and GPT currently underperforms humans in some areas and overperforms them in others.