What the hell is going on inside neural networks? | Chris Olah

_Originally released August 2021._ Big machine learning models can identify plant species better than any human, write passable essays, beat you at Starcraft 2, figure out how a photo of Tobey Maguire and the word ‘spider’ are related, solve the 60-year-old ‘protein folding problem’, diagnose some diseases, play romantic matchmaker, write solid computer code, and offer questionable legal advice. Humanity made these amazing and ever-improving tools. So how do our creations work? In short: we don’t know. Chris Olah finds this both absurd and unacceptable. Over the last ten years he has been a leader in the effort to unravel what’s really going on inside these black boxes. As part of that effort he helped create the famous DeepDream visualisations at Google Brain, reverse engineered the CLIP image classifier at OpenAI, and is now continuing his work at Anthropic. ---- The 80,000 Hours Podcast features unusually in-depth conversations about the world’s most pressing problems and what you can do to solve them. Learn more, read the summary and find the full transcript on the 80,000 Hours website: https://80000hours.org/podcast/episodes/chris-olah-interpretability-research/