← Back to context Comment by rvz 10 hours ago [flagged] 6 comments rvz Reply jcims 10 hours ago We're allowed to have our ceremonies. kridsdale3 10 hours ago Thank you. If this whole thing isn't fun, it isn't worth doing. user43928 10 hours ago You don't think it's useful to learn whether a model's "intelligence" generalizes beyond the tasks and modalities it is usually optimized for? TylerE 10 hours ago Absolutely not. Makes about as much sense as judging a car based on how good an airplane it makes. lumirth 10 hours ago Have you considered that the single most impressive breakthrough of LLMs as a technology is their ability to generalize beyond what they were explicitly trained on? Great analogy, pal, but LLMs aren't cars. user43928 10 hours ago I disagree. If GPT-7 can draw the Mona Lisa in MS Paint via computer use, this would be interesting.That it isn't the most efficient way to achieve the same end result is irrelevant.
jcims 10 hours ago We're allowed to have our ceremonies. kridsdale3 10 hours ago Thank you. If this whole thing isn't fun, it isn't worth doing.
user43928 10 hours ago You don't think it's useful to learn whether a model's "intelligence" generalizes beyond the tasks and modalities it is usually optimized for? TylerE 10 hours ago Absolutely not. Makes about as much sense as judging a car based on how good an airplane it makes. lumirth 10 hours ago Have you considered that the single most impressive breakthrough of LLMs as a technology is their ability to generalize beyond what they were explicitly trained on? Great analogy, pal, but LLMs aren't cars. user43928 10 hours ago I disagree. If GPT-7 can draw the Mona Lisa in MS Paint via computer use, this would be interesting.That it isn't the most efficient way to achieve the same end result is irrelevant.
TylerE 10 hours ago Absolutely not. Makes about as much sense as judging a car based on how good an airplane it makes. lumirth 10 hours ago Have you considered that the single most impressive breakthrough of LLMs as a technology is their ability to generalize beyond what they were explicitly trained on? Great analogy, pal, but LLMs aren't cars. user43928 10 hours ago I disagree. If GPT-7 can draw the Mona Lisa in MS Paint via computer use, this would be interesting.That it isn't the most efficient way to achieve the same end result is irrelevant.
lumirth 10 hours ago Have you considered that the single most impressive breakthrough of LLMs as a technology is their ability to generalize beyond what they were explicitly trained on? Great analogy, pal, but LLMs aren't cars.
user43928 10 hours ago I disagree. If GPT-7 can draw the Mona Lisa in MS Paint via computer use, this would be interesting.That it isn't the most efficient way to achieve the same end result is irrelevant.
We're allowed to have our ceremonies.
Thank you. If this whole thing isn't fun, it isn't worth doing.
You don't think it's useful to learn whether a model's "intelligence" generalizes beyond the tasks and modalities it is usually optimized for?
Absolutely not. Makes about as much sense as judging a car based on how good an airplane it makes.
Have you considered that the single most impressive breakthrough of LLMs as a technology is their ability to generalize beyond what they were explicitly trained on? Great analogy, pal, but LLMs aren't cars.
I disagree. If GPT-7 can draw the Mona Lisa in MS Paint via computer use, this would be interesting.
That it isn't the most efficient way to achieve the same end result is irrelevant.