quote
active
quote:i-don-t-follow-ai-alignment-research-in-any-depth-but-i-am-noticing-a-striking-disconnect-between-the-concepts-appearing-in-those-discussions-and-recent-advances-in-ai-especially-gpt-3I don't follow AI alignment research in any depth, but I am noticing a striking disconnect between the concepts appearing in those discussions and recent advances in AI, especially GPT-3.
Quote from a question that sparked the post, highlighting the gap between theory and practice.
Source paper
extracted_fromNeighborhood — ranked by edge-count
Frameworks (1)
framework
- Agentic AI ontologyassociated_withThe traditional alignment framework focusing on agents optimized to pursue goals.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Deflates the novelty of AI alignment by pointing to its structural identity with intergenerational value transmission
- Field within which this work has implications for evaluating alignment progress.
- Central thesis of the paper — the framing premise from which all other arguments follow
- The broader domain for which ESR has dual implications: resistance to adversarial manipulation vs. interference with safety interventions
- HHH training framework that Claude was trained with prior to experiments
- Key rhetorical and philosophical argument establishing continuity between AI concerns and child-rearing