Comment by tsimionescu
5 months ago
Are you suggesting that OpenAI published a paper assessing their own models on real-world problems, but failed to properly use their own models? And/or that you know better than OpenAI scientists how to use OpenAI models most effectively?
thou shall not question the high priests
That's not what I'm saying.
But telling us that the designers of a product are stupid and don't know how to use their own product when they're disclosing its limitations should really come with more than a "trust me bro" as evidence.