Sublime
An inspiration engine for ideas
I have claimed that Auto-Regressive LLMs are exponentially diverging diffusion processes.
Here is the argument:
Let e be the probability that any generated token exits the tree of "correct" answers.
Then the probability that an answer of length n is correct is (1-e)^n
1/... See more
Argues that everyone models, some just do so explicitly and others fool themselves into thinking that they do not model. The author provides compelling reasons for why modelling is important and why people should engage in people. (good companion for Daniel Kahneman's Thinking Fast and Slow, very relevant for corporate environments). Core arguments... See more
Joshua M Epstein • Why Model? | Santa Fe Institute
Problems like this are why we say that if anyone builds it, everyone dies. If all the complications were visible early, and had easy solutions, then we’d be saying that if any fool builds it, everyone dies, and that would be a different situation. But when some of the problems stay out of sight? When some complications inevitably go unforeseen?
... See moreEliezer Yudkowsky • If Anyone Builds It, Everyone Dies: Why Superhuman AI Would Kill Us All
this mustafa suleyman blog is SO interesting — i'm not sure i've seen an AI leader write such strong opinions *against* model welfare, machine consciousness etc https://t.co/sQiXM3zwTI https://t.co/NjueLb3Xpe
bummed to see the capital allocators aren't safe post-agi either https://t.co/ggmJ4tlfM2
I'm one of those in-the-trenches LLM researchers. I haven't participated much in the AI or AI safety discourse on Twitter.
After having read and thought through various arguments for and against AI existential risk, here's a summary of my current beliefs.
Sherjil Ozairx.com
Your butler doesn't need a PHD... but he does need to live in your house.
Why small ‘dumb’ models win, and expensive big models cost a lot, and get paid very little (just like real PHDs) https://t.co/TXBicAixrX
Nick Bostrom