23 Feb 2020 20:47 UTC

18 points

4 comments15 min readLW link

[Question] Do you know any human-human communication models?

ld9723 Feb 2020 20:20 UTC

3 points

2 comments4 min readLW link

UML XII: Dimensionality Reduction

Rafael Harth23 Feb 2020 19:44 UTC

9 points

0 comments9 min readLW link

Training Regime Day 9: Double-Crux

Mark Xu23 Feb 2020 18:08 UTC

12 points

0 comments3 min readLW link

Northwest Passage Update

jefftk23 Feb 2020 3:30 UTC

11 points

2 comments1 min readLW link

(www.jefftk.com)

Predictive coding and motor control

Steven Byrnes23 Feb 2020 2:04 UTC

22 points

3 comments4 min readLW link

Continuous Improvement: Insights from ‘Topology’

TurnTrout22 Feb 2020 21:58 UTC

30 points

4 comments4 min readLW link

[Question] How much delay do you generally have between having a good new idea and sharing that idea publicly online?

Mati_Roy22 Feb 2020 20:03 UTC

10 points

10 comments1 min readLW link

Cambridge LW/SSC Meetup

NoSignalNoNoise22 Feb 2020 19:56 UTC

6 points

0 comments1 min readLW link

Training Regime Day 8: Noticing

Mark Xu22 Feb 2020 19:47 UTC

30 points

7 comments3 min readLW link 2 reviews

Why SENS makes sense

emanuele ascani22 Feb 2020 16:28 UTC

28 points

2 comments31 min readLW link

[Question] What do you make of AGI:unaligned::spaceships:not enough food?

Ronny Fernandez22 Feb 2020 14:14 UTC

4 points

3 comments1 min readLW link

Jaan Tallinn’s Philanthropic Pledge

jaan22 Feb 2020 10:03 UTC

78 points

1 comment1 min readLW link

Gary Marcus: Four Steps Towards Robust Artificial Intelligence

Matthew Barnett22 Feb 2020 3:28 UTC

13 points

3 comments5 min readLW link

(arxiv.org)

Playing with Arpeggiators

jefftk22 Feb 2020 3:10 UTC

7 points

0 comments1 min readLW link

(www.jefftk.com)

Attainable Utility Preservation: Empirical Results

TurnTrout and nealeratzlaff

22 Feb 2020 0:38 UTC

66 points

8 comments10 min readLW link 1 review

Will AI undergo discontinuous progress?

Sammy Martin21 Feb 2020 22:16 UTC

27 points

21 comments20 min readLW link

Theory and Data as Constraints

johnswentworth21 Feb 2020 22:00 UTC

65 points

7 comments4 min readLW link

Training Regime Day 7: Goal Factoring

Mark Xu21 Feb 2020 17:55 UTC

13 points

6 comments5 min readLW link

You are an optimizer. Act like it!

agentydragon20 Feb 2020 23:46 UTC

3 points

2 comments2 min readLW link

Goal-directed = Model-based RL?

adamShimi20 Feb 2020 19:13 UTC

21 points

10 comments3 min readLW link

Training Regime Day 6: Seeking Sense

Mark Xu20 Feb 2020 17:33 UTC

10 points

6 comments7 min readLW link

Curiosity Killed the Cat and the Asymptotically Optimal Agent

michaelcohen20 Feb 2020 17:28 UTC

28 points

15 comments1 min readLW link

[Question] How do you survive in the humanities?

polymathwannabe20 Feb 2020 15:19 UTC

29 points

20 comments2 min readLW link

Making Sense of Coronavirus Stats

jmh20 Feb 2020 15:12 UTC

23 points

28 comments2 min readLW link

Mapping downside risks and information hazards

MichaelA, JustinShovelain and David_Kristoffersson

20 Feb 2020 14:46 UTC

23 points

0 comments9 min readLW link

Tessellating Hills: a toy model for demons in imperfect search

DaemonicSigil20 Feb 2020 0:12 UTC

97 points

18 comments2 min readLW link

EA Kansas City planning meetup, discussion & open questions

samstowers19 Feb 2020 23:12 UTC

7 points

1 comment2 min readLW link

On unfixably unsafe AGI architectures

Steven Byrnes19 Feb 2020 21:16 UTC

33 points

8 comments5 min readLW link

[AN #87]: What might happen as deep learning scales even further?

Rohin Shah19 Feb 2020 18:20 UTC

28 points

0 comments4 min readLW link

(mailchi.mp)

Training Regime Day 5: TAPs

Mark Xu19 Feb 2020 18:11 UTC

26 points

0 comments7 min readLW link

[Question] Does donating to EA make sense in light of the mere addition paradox ?

George3d619 Feb 2020 14:14 UTC

8 points

8 comments2 min readLW link

Stuck Exploration

Chris_Leong19 Feb 2020 12:31 UTC

14 points

6 comments1 min readLW link

[Question] Does anyone have a recommended resource about the research on behavioral conditioning, reinforcement, and shaping?

Eli Tyre19 Feb 2020 3:58 UTC

7 points

3 comments1 min readLW link

Assembling Sets for Contra

jefftk19 Feb 2020 3:40 UTC

8 points

2 comments3 min readLW link

(www.jefftk.com)

[Question] Is there an intuitive way to explain how much better superforecasters are than regular forecasters?

William_S19 Feb 2020 1:07 UTC

16 points

5 comments1 min readLW link

We Want MoR (HPMOR Discussion Podcast) Completes Book One

moridinamael19 Feb 2020 0:34 UTC

31 points

0 comments1 min readLW link

[Question] Is there software for goal factoring?

philip_b18 Feb 2020 19:55 UTC

11 points

4 comments1 min readLW link

What are information hazards?

MichaelA18 Feb 2020 19:34 UTC

41 points

15 comments4 min readLW link

Blog Post Day (Unofficial)

Daniel Kokotajlo18 Feb 2020 19:05 UTC

49 points

8 comments1 min readLW link

Big Yellow Tractor (Filk)

Gordon Seidoh Worley18 Feb 2020 18:43 UTC

14 points

3 comments1 min readLW link

Training Regime Day 4: Murphyjitsu

Mark Xu18 Feb 2020 17:33 UTC

31 points

0 comments7 min readLW link

[Question] In a rational world is there a place for ideology?

wachichornia18 Feb 2020 17:09 UTC

2 points

3 comments1 min readLW link

(In)action rollouts

Stuart_Armstrong18 Feb 2020 14:48 UTC

11 points

2 comments2 min readLW link

Counterfactuals versus the laws of physics

Stuart_Armstrong18 Feb 2020 13:21 UTC

16 points

0 comments1 min readLW link

How to actually switch to an artificial body – Gradual remapping

George3d618 Feb 2020 13:19 UTC

9 points

3 comments18 min readLW link

(blog.cerebralab.com)

Wireheading and discontinuity

Michele Campolo18 Feb 2020 10:49 UTC

21 points

4 comments3 min readLW link

Set Ups and Summaries

Elizabeth18 Feb 2020 5:00 UTC

14 points

1 comment4 min readLW link

(acesounderglass.com)

[Productivity] How not to use “Important // Not Urgent”

aaq17 Feb 2020 23:42 UTC

22 points

0 comments1 min readLW link

Training Regime Day 3: Tips and Tricks

Mark Xu17 Feb 2020 18:53 UTC

24 points

5 comments11 min readLW link