Center for AI Safety

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• AI Safetyconcept0.841
  The project of ensuring AI systems do not harm humans (and other animals); sometimes in tension with AI welfare.
• AI Alignment and Safetyconcept0.754
  The broader domain for which ESR has dual implications: resistance to adversarial manipulation vs. interference with safety interventions
• Stanford Institute for Human-Centered Artificial Intelligenceinstitute0.736
  Provided funding support for the research.
• How Should Ai Safety And Ethics Frameworks Bequestion0.724
• Centersconcept0.722
  Primary entities of wholeness that arise from configurations and are activated in space; they have different levels of strength or coherence and are intensified by relationships with other centers.
• AI Control: Improving Safety Despite Intentional Subversion (Greenblatt et al. 2024)concept0.722
  Related work studying capability of LLMs to subvert safety measures if severely misaligned
• Ai Ethicsconcept0.716
• MIT AI Labinstitute0.715
  Co-founded by Marvin Minsky; gatekeeping institution for AI research; holder of power over research agenda.