Stop "reinventing" everything to "solve" alignment

<p>Integrating some non computing science into reinforcement learning from human feedback can give us the models we want.<br />This is AI generated audio with Python and 11Labs.<br />Source code: <a class="linkified" href="https://github.com/natolambert/interconnects-tools" target="_blank">https://github.com/natolambert/interconnects-tools</a><br />Original post: <a class="linkified" href="https://www.interconnects.ai/p/reinventing-llm-alignment" target="_blank">https://www.interconnects.ai/p/reinventing-llm-alignment</a></p><p>0:00 Stop "reinventing" everything to "solve" AI alignment<br />2:19 Social Choice for AI Alignment: Dealing with Diverse Human Feedback<br />7:03 OLMo 1.7 7B: A truly open model with actually good benchmarks</p><p><br />Fig 1: <a class="linkified" href="https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_013.png" target="_blank">https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_013.png</a><br />Fig 2: <a class="linkified" href="https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_015.png" target="_blank">https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_015.png</a><br />Fig 3: <a class="linkified" href="https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_018.png" target="_blank">https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_018.png</a><br />Fig 4: <a class="linkified" href="https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_024.png" target="_blank">https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_024.png</a><br />Fig 5: <a class="linkified" href="https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_027.png" target="_blank">https://huggingface.co/datasets/natolambert/interconnects-figures/resolve/main/reinvention/img_027.png</a></p> <br /><br />This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit <a href="https://www.interconnects.ai/subscribe?utm_medium=podcast&#38;utm_campaign=CTA_2">www.interconnects.ai/subscribe</a>