Myopia

Tag

Partial Agency

abramdemski27 Sep 2019 22:04 UTC

60 points

18 comments9 min readLW link

The Credit Assignment Problem

abramdemski8 Nov 2019 2:50 UTC

95 points

40 comments17 min readLW link 1 review

Towards a mechanistic understanding of corrigibility

evhub22 Aug 2019 23:20 UTC

47 points

26 comments6 min readLW link

Steering Behaviour: Testing for (Non-)Myopia in Language Models

Evan R. Murphy and Megan Kinniment

5 Dec 2022 20:28 UTC

39 points

17 comments10 min readLW link

Open Problems with Myopia

Mark Xu and evhub

10 Mar 2021 18:38 UTC

65 points

16 comments8 min readLW link

Defining Myopia

abramdemski19 Oct 2019 21:32 UTC

32 points

18 comments8 min readLW link

LCDT, A Myopic Decision Theory

adamShimi and evhub

3 Aug 2021 22:41 UTC

57 points

50 comments15 min readLW link

Arguments against myopic training

Richard_Ngo9 Jul 2020 16:07 UTC

62 points

39 comments12 min readLW link

You can still fetch the coffee today if you’re dead tomorrow

davidad9 Dec 2022 14:06 UTC

63 points

16 comments5 min readLW link

An overview of 11 proposals for building safe advanced AI

evhub29 May 2020 20:38 UTC

206 points

36 comments38 min readLW link 2 reviews

Evan Hubinger on Homogeneity in Takeoff Speeds, Learned Optimization and Interpretability

Michaël Trazzi8 Jun 2021 19:20 UTC

28 points

0 comments55 min readLW link

Understanding and controlling auto-induced distributional shift

LRudL13 Dec 2021 14:59 UTC

26 points

3 comments16 min readLW link

Bayesian Evolving-to-Extinction

abramdemski14 Feb 2020 23:55 UTC

38 points

13 comments5 min readLW link

Random Thoughts on Predict-O-Matic

abramdemski17 Oct 2019 23:39 UTC

34 points

3 comments9 min readLW link

The Parable of Predict-O-Matic

abramdemski15 Oct 2019 0:49 UTC

316 points

41 comments14 min readLW link 2 reviews

Self-Fulfilling Prophecies Aren’t Always About Self-Awareness

John_Maxwell18 Nov 2019 23:11 UTC

14 points

7 comments4 min readLW link

The Dualist Predict-O-Matic ($100 prize)

John_Maxwell17 Oct 2019 6:45 UTC

16 points

35 comments5 min readLW link

Why GPT wants to mesa-optimize & how we might change this

John_Maxwell19 Sep 2020 13:48 UTC

55 points

33 comments9 min readLW link

2019 Review Rewrite: Seeking Power is Often Robustly Instrumental in MDPs

TurnTrout23 Dec 2020 17:16 UTC

35 points

0 comments4 min readLW link

(www.lesswrong.com)

Seeking Power is Often Convergently Instrumental in MDPs

TurnTrout and Logan Riggs

5 Dec 2019 2:33 UTC

159 points

39 comments17 min readLW link 2 reviews

(arxiv.org)

GPT-4 busted? Clear self-interest when summarizing articles about itself vs when article talks about Claude, LLaMA, or DALL·E 2

Christopher King31 Mar 2023 17:05 UTC

6 points

4 comments4 min readLW link

Fighting Akrasia: Incentivising Action

Gordon Seidoh Worley29 Apr 2009 13:48 UTC

11 points

58 comments2 min readLW link

Graphical World Models, Counterfactuals, and Machine Learning Agents

Koen.Holtman17 Feb 2021 11:07 UTC

6 points

2 comments10 min readLW link

Transforming myopic optimization to ordinary optimization—Do we want to seek convergence for myopic optimization problems?

tailcalled11 Dec 2021 20:38 UTC

12 points

1 comment5 min readLW link

How complex are myopic imitators?

Vivek Hebbar8 Feb 2022 12:00 UTC

26 points

1 comment15 min readLW link

AI safety via market making

evhub26 Jun 2020 23:07 UTC

60 points

45 comments11 min readLW link

Interpretability’s Alignment-Solving Potential: Analysis of 7 Scenarios

Evan R. Murphy12 May 2022 20:01 UTC

52 points

0 comments59 min readLW link

Acceptability Verification: A Research Agenda

David Udell and evhub

12 Jul 2022 20:11 UTC

50 points

0 comments1 min readLW link

(docs.google.com)

Laziness in AI

Richard Henage2 Sep 2022 17:04 UTC

11 points

5 comments1 min readLW link

Generative, Episodic Objectives for Safe AI

Michael Glass5 Oct 2022 23:18 UTC

11 points

3 comments8 min readLW link

Limiting an AGI’s Context Temporally

EulersApprentice17 Feb 2019 3:29 UTC

5 points

11 comments1 min readLW link

Simulators

janus2 Sep 2022 12:45 UTC

596 points

114 comments41 min readLW link

(generative.ink)

Underspecification of Oracle AI

Rubi J. Hudson, Adam Jermyn and Johannes Treutlein

15 Jan 2023 20:10 UTC

30 points

12 comments19 min readLW link

GPT-4 aligning with acasual decision theory when instructed to play games, but includes a CDT explanation that’s incorrect if they differ

Christopher King23 Mar 2023 16:16 UTC

7 points

4 comments8 min readLW link

A crazy hypothesis: GPT-4 already is agentic and is trying to take over the world!

Christopher King24 Mar 2023 1:19 UTC

−1 points

11 comments9 min readLW link

No comments.