Using Dangerous AI, But Safely? - YouTube
Can we keep powerful AI under control, using AI?The Paper: https://arxiv.org/abs/2312.06942AI Lab Watch: https://ailabwatch.org/Thanks to my wonderful patron...
Can we keep powerful AI under control, using AI? How to Help: https://aisafety.info/questions/8TJV/... https://www.aisafety.com/ Sources: The Paper: https://arxiv.org/abs/2312.06942 Links: AI Lab Watch: https://ailabwatch.org/ AI control: https://aisafety.info/questions/NM31/What-is-the-AI-control-research-agenda The case for AI control: https://www.alignmentforum.org/posts/kcKrE9mzEHrdqtDpE/the-case-for-ensuring-that-powerful-ais-are-controlled Thanks to my wonderful patrons: https://www.patreon.com/robertskmiles Steef Tor Barstad John Brewer Timothy Lillicrap Juan Benet Jan van…
saved by
related reading
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- Introduction to AI Control - by Sarah - BlueDot Impactblog.bluedot.org
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
- AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
- [2312.06942] AI Control: Improving Safety Despite Intentional Subversionarxiv.org
- The Case Against AI Control Research — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- 2312.06942arxiv.org
- AI Safety for Fleshy Humans: a whirlwind touraisafety.dance
- The case for ensuring that powerful AIs are controlled — AI Alignment Forumalignmentforum.org
- Reading Listblog.redwoodresearch.org