3 ms·
So the dialectic here is: > AI Industry: Generative AI is sensitive to the semantic properties of code > Credulous Fanatic: Yes! Of course! Here's an infinite
by mjburgess 3y ago
So the dialectic here is:
> AI Industry: Generative AI is sensitive to the semantic properties of code
> Credulous Fanatic: Yes! Of course! Here's an infinite number of cases to confirm that idea
> Scientist: Here's a single case which shows that's false
> Credulous Fanatic: But... "some irrelevant unevidenced point about human capabilities, 101 distractions, repetition of the latest OpenAI press release"
Conclusion: ChatGPT is not sensitive to the semantic properties of code. It's output displays that apparent property in many useful cases.
- TeMPOraL 3y agoNo. The problem here is, "scientists" believe GPT models couldn't possibly be in any way exhibiting forms of thinking or intelligence similar to humans, and so they assume they must be doing some specific kind of computation humans are not, despite every interaction with ChatGPT being evidence to the contrary. They design a test that a human would not pass (despite their claims), but their imagined specific computational system would - and then act all proud and mighty after ChatGPT fails it too. The only real insight from this event is: the authors of this paper imagined ChatGPT to be something it isn't, then demonstrated it in fact isn't it, and think they've discovered something.