• 0 Posts
  • 23 Comments
Joined 1 year ago
cake
Cake day: July 3rd, 2023

help-circle

  • I don’t like the idea of restricting the model’s corpus further. Rather, I think it would be good if it used a bigger corpus, but added the date of origin for each element as further context.

    Separately, I think it could be good to train another LLM to recognize biases in various content, and then use that to add further context for the main LLM when it ingests that content. I’m not sure how to avoid bias in that second LLM, though. Maybe complete lack of bias is an unattainable ideal that you can only approach without ever reaching it.
















  • IQ has very little to do with this. There are some very intelligent people who are also very religious.

    A lot of people confuse intelligence with wisdom. If you considered a human mind like a computer, intelligence would correspond to the CPU and RAM, which determine how fast you think and how much memory you have (and how good it is) whereas wisdom is like the software that runs on the computer.

    Install shitty software, and the most powerful, fastest computer will just give you shit. Garbage in, garbage out, as they say.

    You take a guy like Elon Musk, for example. Clearly intelligent. Definitely not slow. But he’s spectacularly wrong about many things. Because he was not taught right when he was a kid, and he then learned the wrong lessons in life afterwards. Bad software, bad data. Still very intelligent.