UK AISI

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

• UKRI Centre for Doctoral Training in Safe and Trusted AIinstitute0.719
  Funding body supporting Francis Ward and Alex Jackson.
• Constitutional AIframework0.698
  Alignment approach by Anthropic that explicitly trains self-observation; predicts highest baseline and lowest prompt lift.
• AI alignmentconcept0.691
  Field within which this work has implications for evaluating alignment progress.
• AI welfareconcept0.691
  The field concerned with the wellbeing of AI systems, which the paper says must consider benchmark reliability issues from eval awareness.
• AI Safetyconcept0.691
  The project of ensuring AI systems do not harm humans (and other animals); sometimes in tension with AI welfare.
• Intelligence Amplification (IA)concept0.681
  The idea of using machines/systems to magnify human intellectual capability, early AI concept tied to Alexander's Notes.
• Aily Labsinstitute0.681
  Company affiliation of Adam Elwood
• Artificial Intelligenceconcept0.677
  Domain where consciousness theories are being applied to synthetic systems; part of broader context of unconventional embodiments.