Geoffrey Irving - Google Scholar Profile
webCredibility Rating
High quality. Established institution or organization with editorial oversight and accountability.
Rating inherited from publication venue: Google Scholar
This Google Scholar profile for Geoffrey Irving is currently returning a 404 error. Irving is notable for co-authoring the AI Safety via Debate paper and contributions to scalable oversight; his active publications can be found through alternative sources like arXiv or DeepMind's website.
Metadata
Summary
Google Scholar profile page for Geoffrey Irving, an AI safety researcher known for foundational work on AI safety via debate and iterated amplification. The page is currently returning a 404 error and is inaccessible. Irving has contributed significantly to scalable oversight research, particularly at OpenAI and DeepMind.
Key Points
- •Geoffrey Irving is a key researcher in scalable oversight and AI alignment, co-authoring influential papers on AI safety via debate
- •His work on 'AI Safety via Debate' proposes using adversarial debate between AI systems as a mechanism for human oversight of superintelligent systems
- •Irving contributed to iterated amplification research alongside Paul Christiano, exploring methods for scalably supervising AI systems
- •The profile page is currently inaccessible (404 error), limiting direct access to his publication list
- •His research spans formal verification, scalable oversight, and constitutional approaches to AI alignment
Cited by 1 page
| Page | Type | Quality |
|---|---|---|
| Paul Christiano | Person | 39.0 |
Cached Content Preview
**404.** That’s an error. The requested URL `/citations?user=BqAeRdAAAAAJ` was not found on this server. That’s all we know.
367c57adf0c2bc75 | Stable ID: sid_392nAcxhJG