RSS

William_S

Karma: 475 (LW), 19 (AF)

Re­in­force­ment Learn­ing in the Iter­ated Am­plifi­ca­tion Framework

William_S
9 Feb 2019 0:56 UTC
24 points
9 commentsLW link

HCH is not just Me­chan­i­cal Turk

William_S
9 Feb 2019 0:46 UTC
36 points
4 commentsLW link

Am­plifi­ca­tion Dis­cus­sion Notes

William_S
1 Jun 2018 19:03 UTC
41 points
3 commentsLW link

Un­der­stand­ing Iter­ated Distil­la­tion and Am­plifi­ca­tion: Claims and Oversight

William_S
17 Apr 2018 22:36 UTC
70 points
22 commentsLW link

Im­prob­a­ble Over­sight, An At­tempt at In­formed Oversight

William_S
24 May 2017 17:43 UTC
2 points
0 commentsLW link
(william-r-s.github.io)

In­formed Over­sight through Gen­er­al­iz­ing Explanations

William_S
24 May 2017 17:43 UTC
1 point
0 commentsLW link
(william-r-s.github.io)

Pro­posal for an Im­ple­mentable Toy Model of In­formed Oversight

William_S
24 May 2017 17:43 UTC
1 point
0 commentsLW link
(william-r-s.github.io)