Alignment faking in large language models \ Anthropic
A paper from Anthropic's Alignment Science team on Alignment Faking in AI large language models| www.anthropic.com
Quotes about risks from artificial intelligence| PauseAI
A paper from Anthropic's Alignment Science team on Alignment Faking in AI large language models| www.anthropic.com
Educational resources (videos, articles, books) about AI risks and AI alignment| PauseAI
How much do regular people and experts worry about AI risks?| PauseAI
Implement a temporary pause on the training of the most powerful general AI systems.| PauseAI
We're underestimating the progress of AI, and there is a small but realistic chance that we are very close to a superintelligence.| PauseAI
This post discusses how rogue AIs could potentially arise, in order to stimulate thinking and investment in both technical research and societal reforms aimed at minimizing such catastrophic outcomes.| Yoshua Bengio
We call on all AI labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4.| Future of Life Institute
Collected data and analysis from a large survey of machine learning researchers.| AI Impacts
