2  Historical Roots (1950–2015)

3 Historical Roots (1950–2015)

AI safety is not new — the problem was named decades before the methods. Three lineages converge into today’s field.

3.1 Control & alignment

Wiener (1960) gave the first clear statement of the control problem: a machine optimizing a literal goal faster than we can follow, which “we may not know, until too late, when to turn off” (Wiener, 1960). Good (1965) added the intelligence explosion — the last invention “provided the machine is docile enough… to keep under control” (Good, 1965) — the direct ancestor of recursive self-improvement.

3.2 System-safety engineering

Long before ML, Leveson established that safety is a system property, not a component one: end-to-end hazard analysis, not a safe algorithm (Leveson, 1995). This is the root of today’s safety cases and defense-in-depth (Dobbe, 2022).

3.3 Philosophy & x-risk

Omohundro’s basic AI drives (Omohundro, 2008) and Bostrom’s instrumental convergence (Bostrom, 2014) argued capable agents converge on self-preservation and resource acquisition regardless of their goal.

Deep history of AI safety, 1950–2016 1950 · Turing 1960 · Wiener control problem 1965 · Good intelligence explosion 1995 · Leveson system safety 2008 · Omohundro basic AI drives 2014 · Bostrom 2016 · Amodei → Concrete Problems
Note

Cultural background. Fiction framed these ideas long before the research: Asimov’s Three Laws of Robotics (1942) — constraint-based safety; 2001: A Space Odyssey / HAL 9000 (1968) — an agent pursuing its objective to lethal ends; The Terminator / Skynet (1984) — loss of control and runaway capability; Ex Machina (2014) — containment and deceptive alignment. Intuition pumps, not engineering — but they shaped how the public frames every problem in this book.

3.4 Handoff to the empirical era

These threads hand off to Concrete Problems in AI Safety (Amodei et al., 2016), which reframed them as tractable empirical ML problems — where the modern landscape and its timeline begin.