I'll be presenting what I learned about safety engineering at the Center for AI Safety's ML Safety Scholars fellowship. The content will be simple enough for beginners at a high school level to understand. 

Some topics covered include: 

• Examples of failures in lots of engineering applications (from bridges to cars to spacecraft to chemical factories and more).
• Creating quantitative risk equations.
• Traditional safety engineering analyses like Failure Modes and Effects Analysis (FMEA) or Fault Tree Analysis.
• Novel safety engineering analyses like the Systems-Theoretic Accident Model and Process (STAMP). 

This talk is part of a series of talks on technological risks. It'll be followed by:

• An introduction on AI Safety by Joshua Clymer at the Centre for AI Safety. Link to details here.
• An introduction to cyberbiosecurity risks by Kathryn Millet at Biosecure Ltd. Link to details here.

The event will be hosted via Zoom. If you're interested in joining, message @Madhav Malhotra for the link.