foomflops

Chapter 05 · 2013–2021

MIRI: Research

those who can't build, align

Overview

After the early implementation timelines failed, MIRI turned toward decision theory, logical uncertainty, agent foundations, and alignment. The Institute increasingly treated the lack of any known safe path to advanced AI as its central problem.

Meanwhile, deep learning complicated the picture. Progress came through larger models, more data, better chips, and large research organizations, rather than through the small number of decisive architectural breakthroughs the foom model had anticipated. AlphaGo raised serious doubts about that picture; GPT-3 did far more damage.

Predictions in this chapter

Chapter sources