It’s the 1980s. You’re looking out over the autobahn in Germany and suddenly a Mercedes Benz zooms by. Only, there’s no one inside. A neural network is controlling the vehicle. It’s the first self driving car.

There are ever growing cracks: Yet the genie is already out of the bottle.

Why? Human feedback on every output doesn’t scale. What if AI could supervise itself, what framework would you give? Maybe something like what Anthropic’s AI constitution outlines in the below. Be helpful: Provide useful, accurate information Be harmless: Avoid harmful, toxic, or dangerous content Be honest: Don’t lie or provide false information Respect autonomy: Support human agency and choice

A single path splits into two. On the left, we our intended destination, and on the right we have the actual destination. What caused the split? 1. We wanted X outcome (good education, company performance). 2. We measured Y as a proxy for X (test scores, quarterly profits). 3. We optimized for Y instead of…

ChatGPT and Claude, two AI models one built by OpenAI and one by Anthropic, take very different approaches to their models. One of the big points of divergence is in persistent memory. Claude starts each chat from zero. ChatGPT has persistent memory. What are the pros and cons for persistent memory? Pros: Cons: