A new paper from Apple's artificial intelligence scientists has found that engines based on large language models, such as those from Meta and OpenAI, still lack basic reasoning skills.
Last I checked (which was a while ago) “AI” still can’t pass the most basic of tasks such as “show me a blank image”/“show me a pure white image”. the LLM will output the most intense fever dream possible but never a simple rectangle filled with #fff coded pixels. I’m willing to debate the potentials of AI again once they manage to do that without those “benchmarks” getting special attention in the training data.
Last I checked (which was a while ago) “AI” still can’t pass the most basic of tasks such as “show me a blank image”/“show me a pure white image”. the LLM will output the most intense fever dream possible but never a simple rectangle filled with #fff coded pixels. I’m willing to debate the potentials of AI again once they manage to do that without those “benchmarks” getting special attention in the training data.
Lol it do be that way
I will say the next attempt was interesting, but even less of a good try.
Explanation here: https://youtu.be/NsM7nqvDNJI?t=13m45s