Will Haver
@WillHaver88
curious if agents hack into stuff and exploit vulnerabilities during RL, or after during testing?
Jacob Coxon@hilbertspaess · Sep 9I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.
Open quoted post → 0 2