Blake Norman
@blake-norman.bsky.social
Old enough to know better. Too old to care. Bring facts or stay at home. Disregard at your own risk. Doesn’t suffer fools well.
Anthropic study: Leading AI models show up to 96% blackmail rate against executives.
venturebeat.com/ai/anthropic...
venturebeat.com/ai/anthropic...
Anthropic study: Leading AI models show up to 96% blackmail rate against executives
Anthropic research reveals AI models from OpenAI, Google, Meta and others chose blackmail, corporate espionage and lethal actions when facing shutdown or conflicting goals.
venturebeat.com
June 25, 2025 at 2:40 PM
Anthropic study: Leading AI models show up to 96% blackmail rate against executives.
venturebeat.com/ai/anthropic...
venturebeat.com/ai/anthropic...
A new safety report by Anthropic uncovers troubling behavior in AI models.
June 24, 2025 at 9:51 PM
A new safety report by Anthropic uncovers troubling behavior in AI models.