![[Search]](/static/images/search.gif){kind=small}
![[A-Z Index]](/static/images/az.gif){kind=small}
![[Contact]](/static/images/contact.gif){kind=small}
![[University of Cambridge]](/static/images/identifier2.gif){kind=small}
![[Talks.cam]](/static/images/talkslogosmall.gif)
Wednesday 24 January 2018, 17:00-18:30
Amplification and dialogue as mechanisms for safe advanced AI
- 👤 Speaker: Beth Barnes, Computer Lab, University of Cambridge
- 📅 Date & Time: Wednesday 24 January 2018, 17:00 - 18:30
- 📍 Venue: Cambridge University Engineering Department, CBL Seminar room BE4-38. For directions see http://learning.eng.cam.ac.uk/Public/Directions
Questions? Contact
Adrià Garriga Alonso
Abstract
Slides: https://valuealignment.ml/talks/2018-01-24-amplification.pdf
These techniques come at the problem of safety from a fairly different angle than the things we’ve discussed so far.
Amplification is the idea of bootstrapping a trusted core system, increasing its capabilities while maintaining safety properties. Paul Christiano and the OpenAI safety team have worked on these ideas. One current suggestion for how to do this has a lot in common with functional programming. For some more discussion see e.g. https://ai-alignment.com/alba-an-explicit-proposal-for-aligned-ai-17a55f60bbcf
Series This talk is part of the Engineering Safe AI series.
Included in Lists
- Cambridge talks
- Cambridge University Engineering Department, CBL Seminar room BE4-38. For directions see http://learning.eng.cam.ac.uk/Public/Directions
- Chris Davis' list
- Engineering Safe AI
- Trust & Technology Initiative - interesting events
- yk449
Note: Ex-directory lists are not shown.