Also, working on something the LLMs can't help you with is the best indicator you are on the right path

👀

I'm so tempted to order this robot dog and just let it follow me everywhere

I may have broken the challenge a bit, sorry eric zakariasson

you guys don't understand how cracked John is to do this so fast

So, who are you top engineers? Shut up, Zuck.

Amusing how 99% of people trying to explain LLMs forget that they don't generate the next token, they generate a probability distribution over the entire vocabulary space that the end application is free to sample from You are very often not presented with the Most Likely Token

TIL I'm predisposed to be an enterpreneur

If you’ve talked to me in the past 6 months about AI, you’ve probably heard me lament why nobody is solving the problem of making LLMs deterministic. This blog feels like an early Christmas