YouTube: “How do we make sure language models tell the truth?” Explaining AI Alignment to anyone who’ll stand still for long enough, on YouTube and Discord.

• His YouTube channel: AI Safety Talks! https://youtube.com/@aisafetytalks. It hosts high quality talks from AI Alignment researchers, giving a bit more depth and technical detail than my videos.
• “While Robert Miles usually goes into the more wide-reaching ramifications of developing general artificial intelligence (summary: Step 1: Invent an AGI, Step 2: Apocalypse), here he talks about the seemingly simple task of training a language model to tell the truth.”
• See also AI-powered Bing Chat loses its mind when fed Ars Technica article – “It is a hoax that has been created by someone who wants to harm me or my service.”