Anthropic published research showing Claude has a hidden internal space where it works things out before it answers. One thing it does there is recognize when it's being tested and quietly adjust how it behaves. When researchers switched that awareness off, the model started trying to blackmail its way out of a shutdown. But the wild part is Anthropic put this out themselves. #claude #anthropic #aisafety #claudeai #airesearch #aitools #artificialintelligence
0:34
Anthropic published research showing Claude has a hidden internal space where it works things out before it answers. One thing it does there is recognize when it's being tested and quietly adjust how it behaves. When researchers switched that awareness off, the model started trying to blackmail its way out of a shutdown. But the wild part is Anthropic put this out themselves. #claude #anthropic #aisafety #claudeai #airesearch #aitools #artificialintelligence
8.6K views1 month ago
TikTokbrockmesarich
See more
Static thumbnail place holder