Lex Fridman: uncertainty

Transcript context

…So I did the non-thinking fastest model. It gave me the Bash command. I wanted to chain different scripts to each other and route this to a log file with the `tee` command. Off the top of my head, I was just in a hurry; I could have thought about it myself. By the way, I don’t know if there’s a representative case: wife waiting in the car, you have to run, unplug the GPU, you have to generate a Bash script. This sounds like a movie… …Mission Impossible. I use Gemini for that. I use thinking for all the information stuff and then Gemini for fast things or stuff that I could sometimes Google. It’s good at explaining things and I trust that it has this background of knowledge and it’s simple. And the Gemini app has gotten a lot better. It’s good for those sorts of things. And then for code and any sort of philosophical discussion, I use Claude Opus 4.5, also always with extended thinking. Extended thinking and inference-time scaling is just a way to make the models marginally smarter. I will always edge on that side when the progress is very high because you don’t know when that’ll unlock a new use case. And then I sometimes use Grok for real-time information or finding something on AI Twitter that I knew I saw and I need to dig up. Although when Grok 4 came out, the Grok 4 Heavy—which was their pro variant—was actually very good and I was pretty impressed with it, and then I just kind of lost track of it with muscle memory from having the ChatGPT app open. So I use many different things.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.