User contributions
(newest | oldest) View (newer 20 | older 20) (20 | 50 | 100 | 250 | 500)
- 05:06, 23 February 2020 (diff | hist) . . (+28) . . N Goal inference (Redirected page to Value learning) (current) (Tag: New redirect)
- 05:05, 23 February 2020 (diff | hist) . . (+119) . . N Value learning (Created page with "kinds of value learning: * ambitious value learning * narrow value learning ** paul's definition ** rohin's definition")
- 04:52, 23 February 2020 (diff | hist) . . (+550) . . N Human safety problem (Created page with " e.g. "Think of the human as a really badly designed AI with a convoluted architecture that nobody understands, spaghetti code, full of security holes, has no idea what its te...")
- 03:08, 23 February 2020 (diff | hist) . . (+21) . . N AlphaGo Zero (Redirected page to AlphaGo) (current) (Tag: New redirect)
- 02:30, 23 February 2020 (diff | hist) . . (+966) . . N Will there be significant changes to the world prior to some critical AI capability threshold being reached? (Created page with "'''Will there be significant changes to the world prior to some critical AI capability threshold being reached?''' This is currently one of the questions I am most confused ab...")
- 23:25, 22 February 2020 (diff | hist) . . (+23) . . N Evolution analogy (Issa moved page Evolution analogy to Evolution) (current) (Tag: New redirect)
- 23:23, 22 February 2020 (diff | hist) . . (+240) . . N Evolution (Created page with "In discussions of AI risk, evolution is often used as an analogy for the development of AGI. here are some examples: * chimpanzee vs human intelligence * optimization daemo...")
- 23:14, 22 February 2020 (diff | hist) . . (+754) . . N Paperclip maximizer (Created page with "my understanding is that the paperclip maximizer example was intended to illustrate the following two concepts: * orthogonality thesis: intelligence/capability and values...")
- 22:40, 22 February 2020 (diff | hist) . . (+37) . . N IDA (Created page with "# redirect Iterated amplification")
- 22:38, 22 February 2020 (diff | hist) . . (+239) . . N Iterated amplification (Created page with "'''Iterated amplification''' (also called '''iterated distillation and amplification''', and abbreviated '''IDA''') is the technical alignment agenda that Paul Christiano...")
- 22:36, 22 February 2020 (diff | hist) . . (+213) . . N AlphaGo (Created page with "'''AlphaGo''' and its successor '''AlphaGo Zero''' are used to make various points in AI safety. * Rapid capability gain * (for AlphaGo Zero) comparison to Paul Chr...")
- 09:39, 22 February 2020 (diff | hist) . . (+26) . . N Hansonian (Redirected page to Robin Hanson) (current) (Tag: New redirect)
- 09:38, 22 February 2020 (diff | hist) . . (+31) . . N Yudkowskian (Redirected page to Eliezer Yudkowsky) (current) (Tag: New redirect)
- 09:37, 22 February 2020 (diff | hist) . . (+391) . . N Comparison of AI takeoff scenarios (Created page with "{| class="wikitable" |- ! Scenario !! Significant changes to the world prior to critical AI capability threshold being reached? !! Intelligence explosion? !! Decisive strategi...")
- 06:57, 22 February 2020 (diff | hist) . . (+929) . . N Counterfactual of dropping a seed AI into a world without other capable AI (Created page with ""Well yeah, ''if'' we dropped a superintelligence into a world full of humans. But realistically the rest of the world will be undergoing intelligence explosion too. And indee...")
- 08:30, 20 February 2020 (diff | hist) . . (+496) . . N Minimal AGI vs task AGI (Created page with "* I'm not clear on what the difference is here * See MIRI's strategic plan from end of 2017 where they make this distinction * It seems like MIRI went from: ** a one-step view...")
- 08:21, 20 February 2020 (diff | hist) . . (+2,740) . . N My understanding of how IDA works (Created page with "==explanation== '''Stage 0''': In the beginning, Hugh directly rates actions to provide the initial training data on what Hugh approves of. This is used to train <math>A_0</m...")
- 03:48, 20 February 2020 (diff | hist) . . (+55) . . N Simple core algorithm for agency (Redirected page to Simple core of consequentialist reasoning) (current) (Tag: New redirect)
- 00:27, 20 February 2020 (diff | hist) . . (+29) . . N Paul (Redirected page to Paul Christiano) (current) (Tag: New redirect)
- 00:27, 20 February 2020 (diff | hist) . . (+30) . . N Paul christiano (Created page with "# redirect Paul Christiano")
(newest | oldest) View (newer 20 | older 20) (20 | 50 | 100 | 250 | 500)