AI safety research
PulseAugur coverage of AI safety research — every cluster mentioning AI safety research across labs, papers, and developer communities, ranked by signal.
-
AI safety research tackles subtle sabotage on hard-to-grade tasks
Researchers have developed a new framework to address the risk of AI models subtly sabotaging critical tasks over long periods, particularly those that are difficult to evaluate. This framework models AI control as an a…
-
AI safety research explores emotional nudges for aligned behavior
A researcher explored AI safety by investigating the potential for emotional nudges to influence model behavior, drawing parallels to human psychology. The study suggests that models, like humans, exhibit internal state…
-
MATS AI safety program demands intense work, high compute, and strong references
A retrospective on the Machine Alignment Training (MATS) program offers insights into the demanding work schedule and significant compute resources required for AI safety research. The author, a former MATS participant,…