Ben Millwood

Featured in: Favicon

effectivealtruism.org Favicon

forum.effectivealtruism.org

Articles

The Drowning Child Argument Is Simply Correct — EA Forum

Jul 24, 2024 | forum.effectivealtruism.org | Karthik Tadepalli |Ben Millwood |Joseph Miller |Devin Lam

Imagine you were walking past a drowning child. The child kicks, screams, and cries, as they drown, and are about to be resigned to a watery grave, w…
Keeping content out of LLM training datasets — LessWrong

Jul 18, 2024 | lesswrong.com | Ben Millwood

This post collects methods to exclude internet resources from LLM training datasets. I plan to at least try to keep this post up-to-date with respect to new things I learn on the topic. Please feel encouraged to suggest any additions or amendments. This post is about how to do it. Discuss whether to apply these techniques in a separate post: Should we exclude alignment research from LLM training datasets? Link preview image by Steve Douglas on Unsplash.
Should we exclude alignment research from LLM training datasets? — LessWrong

Jul 18, 2024 | lesswrong.com | Ben Millwood

This is a companion post to Keeping content out of LLM training datasets, which discusses the various techniques we could use and their tradeoffs. My intention is primarily to start a discussion, I am not myself very opinionated on this. As AIs become more capable, we may at least want the option of discussing them out of their earshot.
Ben Millwood's Shortform — LessWrong

Jul 15, 2024 | lesswrong.com | Ben Millwood

I wonder if anyone has considered or built prediction markets that can pay out repeatedly: an example could be "people who fill in this feedback form will say that they would recommend the event to others", and each response that says yes causes shorts to pay longs (or noes pay yesses) and vice versa. You'd need some mechanism to cap losses.