The ML community is fond of adopting methods from safety & security engineering. But the rampant co-opting and misuse of established terms and techniques (e.g., “safety”, red teaming) is counterintuitive to actual safety. So we wrote a paper on it: d | tweet by Dr Heidy Khlaaf (هايدي خلاف)

Timnit Gebru @timnitGebru · Mar 10, 2023

Please read this paper & thread about actual safety rather than the co-opted "AI safety" which is the opposite 👇🏽

Tweet Mar 10, 2023

by Dr Heidy Khlaaf (هايدي خلاف)

Recommended by 1 person

1 mention