The training data set is a very weirdly undefined thing in this case which is sort of like the weirdest cases humans can come up with. And once you start training the model on like adversarial examples that people have found where it was making mistakes then it gets a lot more suspicious of stuff like that. It's funny I said someone posted about this to Facebook I didn't realize this was your project where they were like giving an examples like of a parent slowly and lovingly suffocating their childhood death right? ExactlyYes, we're currently pushing for the goal of no false negatives and 60% false positive rate.
Read the full transcript here.
How hard is it to arrive at true beliefs about the world? How can you find enjoyment in being wrong? When presenting claims that will be scrutinized by others, is it better to hedge and pad the claims in lots of caveats and uncertainty, or to strive for a tone that matches (or perhaps even exaggerates) the intensity with which you hold your beliefs? Why should you maybe focus on drilling small skills when learning a new skill set? What counts as a "simple" question? How can you tell when you actually understand something and when you don't? What is "cargo culting"? Which features of AI are likely in the future to become existential threats? What are the hardest parts of AI research? What skills will we probably really wish we had on the eve of deploying superintelligent AIs?
Buck Shlegeris is the CTO of Redwood Research, an independent AI alignment research organization. He currently leads their interpretability research. He previously worked on research and outreach at the Machine Intelligence Research Institute. His website is shlegeris.com.
Staff
Music
Affiliates