Alignment By Default — AI Alignment Forum

alignmentforum.org · 13,980 words · saved by 1 readers

Suppose AI continues on its current trajectory: deep learning continues to get better as we throw more data and compute at it, researchers keep trying random architectures and using whatever seems to work well in practice. Do we end up with aligned AI “by default”? I think there’s at least a plausible trajectory in which the answer is “yes”. Not very likely - I’d put it at ~10% chance - but plausible. In fact, there’s at least an argument to be made that alignment-by-default is more likely to work than many fancy alignment proposals, including IRL variants and HCH-family methods. This post presents the rough models and arguments. I’ll break it down into two main pieces: Ultimately, we’ll consider a semi-supervised/transfer-learning style approach, where we first do some unsupervised learning and hopefully “learn human values” before starting the supervised/reinforcement part. As background, I will assume you’ve read some of the core material about human values from the sequences, inclu

x Alignment By Default — AI Alignment Forum Best of LessWrong 2020 Abstraction Natural Abstraction AI Frontpage 64 Alignment By Default by johnswentworth 12th Aug 2020 14 min read 101 64 Suppose AI continues on its current trajectory: deep learning continues to get better as we throw more data and compute at it, researchers keep trying random architectures and using whatever seems to work well in practice. Do we end up with aligned AI “by default”? I think there’s at least a plausible trajectory in which the answer is “yes”. Not very likely - I’d put it at ~10% chance - but plausible. In fact,

Alignment By Default — AI Alignment Forum

related reading