Things I read last week… (WB 12 Sep 2022
“We analyze the expected behavior of an advanced artificial agent with a learned goal planning in an unknown environment. Given a few assumptions, we argue that it will encounter a fundamental ambiguity in the data about its goal. For example, if we provide a large reward to indicate that something about the world is satisfactory to us, it may hypothesize that what satisfied us was the sending of the reward itself; no observation can refute that. Then we argue that this ambiguity will lead it to intervene in whatever protocol we set up to provide data for the agent about its goal.”
– On controlling AI.
Predicting odours from their molecular structure.
How ML transformers seem to mimic parts of the brain.
Examples of using DALL-E 2.
Review of futurist predictions.
The future of EDA tools for the semi-conductor industry.
Lex Fridman interviews DeepMind’s Demis Hassabis. [YouTube]
The history of Bell Labs. [YouTube]