AI ALIGNMENT FORUMTags
AF

AI-assisted/AI automated Alignment

EditHistorySubscribe

Help improve this page (1 flag)

EditHistorySubscribe

Help improve this page (1 flag)

AI-assisted/AI automated Alignment

Contributors

Not obviously the best name for this tag, but maybe good to explore/rename. Wiki-tags are publicly editable!

Posts tagged AI-assisted/AI automated Alignment

2

Nicholas Kees Dupuis, janus

7mo

20

1

42Beliefs and Disagreements about Automating Alignment Research

1y

0

1

57[Linkpost] Introducing Superalignment

3mo

11

1

47Godzilla Strategies

1y

19

1

29Cyborg Periods: There will be multiple AI transitions

Jan_Kulveit, rosehadshar

7mo

2

0

15A survey of tool use and workflows in alignment research

Logan Riggs Smith, Jan Hendrik Kirchner, janus, Jacques Thibodeau

2y

3

1

6Model-driven feedback could amplify alignment failures

8mo

0

1

7Making it harder for an AGI to "trick" us, with STVs

Tor Økland Barstad

1y

0

1

7Getting from an unaligned AGI to an aligned AGI?

Tor Økland Barstad

1y

0

1

7Alignment with argument-networks and assessment-predictions

Tor Økland Barstad

10mo

0

1

4AI-assisted list of ten concrete alignment things to do right now

1y

1

1

80Ngo and Yudkowsky on alignment difficulty

Eliezer Yudkowsky, Richard Ngo

2y

53

1

40[Link] Why I’m optimistic about OpenAI’s alignment approach

10mo

12

1

32Results from a survey on tool use and workflows in alignment research

Jacques Thibodeau, Jan Hendrik Kirchner, janus, Logan Riggs Smith

9mo

0

1

35Human Mimicry Mainly Works When We’re Already Close

1y

4