Attempts at Forwarding Speed Priors

james.lucassen and evhub

24 Sep 2022 5:49 UTC

18 points

0 comments18 min readLW link

Interpreting Neural Networks through the Polytope Lens

Sid Black, Lee Sharkey, Connor Leahy, beren, CRG, merizian, EricWinsor and Dan Braun

23 Sep 2022 17:58 UTC

106 points

8 comments33 min readLW link

Methodological Therapy: An Agenda For Tackling Research Bottlenecks

adamShimi, Lucas Teixeira and remember

22 Sep 2022 18:41 UTC

47 points

2 comments9 min readLW link

Toy Models of Superposition

evhub21 Sep 2022 23:48 UTC

54 points

2 comments5 min readLW link

(transformer-circuits.pub)

Announcing AISIC 2022 - the AI Safety Israel Conference, October 19-20

Davidmanheim21 Sep 2022 19:32 UTC

12 points

0 comments1 min readLW link

Nearcast-based “deployment problem” analysis

HoldenKarnofsky21 Sep 2022 18:52 UTC

61 points

2 comments26 min readLW link

Towards deconfusing wireheading and reward maximization

leogao21 Sep 2022 0:36 UTC

47 points

7 comments4 min readLW link

Doing oversight from the very start of training seems hard

peterbarnett20 Sep 2022 17:21 UTC

14 points

3 comments3 min readLW link

PIBBSS (AI alignment) is hiring for a Project Manager

Nora_Ammann19 Sep 2022 13:54 UTC

9 points

0 comments1 min readLW link

The Inter-Agent Facet of AI Alignment

Michael Oesterle18 Sep 2022 20:39 UTC

12 points

1 comment5 min readLW link

Summaries: Alignment Fundamentals Curriculum

Leon Lang18 Sep 2022 13:08 UTC

43 points

3 comments1 min readLW link

(docs.google.com)

Inner alignment: what are we pointing at?

lcmgcd18 Sep 2022 11:09 UTC

7 points

1 comment1 min readLW link

Refine’s Third Blog Post Day/Week

adamShimi17 Sep 2022 17:03 UTC

17 points

0 comments1 min readLW link

Prize and fast track to alignment research at ALTER

Vanessa Kosoy17 Sep 2022 16:58 UTC

60 points

4 comments3 min readLW link

Takeaways from our robust injury classifier project [Redwood Research]

DMZ17 Sep 2022 3:55 UTC

120 points

9 comments6 min readLW link

Refine Blogpost Day #3: The shortforms I did write

Self-Embedded Agent16 Sep 2022 21:03 UTC

20 points

0 comments1 min readLW link

Levels of goals and alignment

zeshen16 Sep 2022 16:44 UTC

25 points

4 comments6 min readLW link

ordering capability thresholds

carado16 Sep 2022 16:36 UTC

24 points

0 comments4 min readLW link

(carado.moe)

Representational Tethers: Tying AI Latents To Human Ones

Paul Bricman16 Sep 2022 14:45 UTC

26 points

0 comments16 min readLW link

AGI safety researchers should focus (only/mostly) on deceptive alignment

Marius Hobbhahn15 Sep 2022 13:38 UTC

38 points

12 comments12 min readLW link