| ▲ | mbowcut2 a day ago | |||||||||||||
I genuinely can't tell if this is sincere or sarcastic. | ||||||||||||||
| ▲ | hansvm a day ago | parent | next [-] | |||||||||||||
My best guess is it's sincere. That's been a core observation of LLMs for awhile. Filtered random search is basically an inefficient gradient descent. If you apply even a poor-quality "gradient" to a lot of problems with infinite compute (with large LLM budgets), it doesn't take that good of an LLM to accomplish great things from time to time. | ||||||||||||||
| ||||||||||||||
| ▲ | qup a day ago | parent | prev [-] | |||||||||||||
There's enough information available to decide. Start with the title of the article | ||||||||||||||