On: LLMs are bullshitters. But that doesn't mean they're not useful

[pengaru]

This is like the LLM era version of the search bubble that prevented people from having the same search results for ostensibly identical searches.

Also keep in mind that LLMs are stochastic by design. If you haven't seen it, Karpathy's excellent "deep dive into LLMs like chatgpt" video[0] explains and demonstrates this aspect pretty well:

[0] https://www.youtube.com/watch?v=7xTGNNLPyMI