“We have identified the root cause which resulted in unauthorized posts on this account today. We have confirmed that no Anthropic systems or services were compromised or involved in this incident. We’re working with @X to better understand this situation.” / X
https://x.com/AnthropicAI/status/1869139895400399183
“Anthropic introduced Clio, a new system that reveals patterns in how people actually use AI The research gives detailed insights into real-world AI adoption across the world Really interesting data in this thread
https://x.com/adcock_brett/status/1868341108192788625
Alignment faking in large language models \ Anthropic
https://www.anthropic.com/research/alignment-faking
