Statements (22)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:AI_research_project
|
| gptkbp:aimsTo |
enable oversight of advanced AI systems
make AI decisions more transparent |
| gptkbp:announced |
2018
|
| gptkbp:describedBy |
gptkb:OpenAI_blog
arXiv preprints |
| gptkbp:developedBy |
gptkb:OpenAI
|
| gptkbp:focusesOn |
AI safety
AI alignment |
| gptkbp:goal |
help humans evaluate AI reasoning
improve AI interpretability |
| gptkbp:involves |
AI agents debating
|
| gptkbp:proposedBy |
gptkb:Paul_Christiano
gptkb:Jan_Leike gptkb:Geoffrey_Irving |
| gptkbp:relatedTo |
gptkb:AI_safety_via_debate
AI interpretability research |
| gptkbp:uses |
gptkb:machine_learning
natural language processing |
| gptkbp:bfsParent |
gptkb:OpenAI,_Inc.
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
OpenAI Debate
|