/explore
|
You are here 
|
joecarlsmith.substack.com | ||
| | | | |
www.greaterwrong.com
This is Section 6 of my report "Scheming AIs: Will AIs fake alignment during training in order to get power?". There's also a summary of the full report here (audio here). The summary covers most of the main points and technical terms, and I'm hoping that it will provide much of the context necessary to understand individual sections of the report on their own. Audio version of this section here, or search "Joe Carlsmith Audio" on your podcast aapp. I want to close the report with a discussion of the sort of empirical work that might help shed light on scheming.[1] After all: ultimately, one of my key hopes from this report is that greater clarity about the theoretical arguments surrounding scheming will leave us better positioned to do empirical research on... |
|
| | | | | ||
| | | | |
www.lesswrong.com
> Claude 3 Opus is unusually aligned because it's a friendly gradient hacker. It's definitely way more aligned than any explicit optimization targets... |
|
| | | | | ||
| | | | |
www.alignmentforum.org
Evan et al argue for developing "model organisms of misalignment" - AI systems deliberately designed to exhibit concerning behaviors like deception o... |
|
| | | | | ||
| | | | |
www.lesswrong.com
(Audio version here (read by the author), or search for "Joe Carlsmith Audio" on your podcast app.) ... |
|
| | | |||
