Chris_Leong

Karma: 7,605

Reverse Regulatory Capture

Chris_LeongApr 11, 2024, 2:40 AM

12 points

3 comments1 min readLW link

On the Confusion between Inner and Outer Misalignment

Chris_LeongMar 25, 2024, 11:59 AM

17 points

10 comments1 min readLW link

The Best Essay (Paul Graham)

Chris_LeongMar 11, 2024, 7:25 PM

25 points

2 comments1 min readLW link

(paulgraham.com)

[Question] Can we get an AI to “do our alignment homework for us”?

Chris_LeongFeb 26, 2024, 7:56 AM

53 points

33 comments1 min readLW link

[Question] What’s the theory of impact for activation vectors?

Chris_LeongFeb 11, 2024, 7:34 AM

61 points

12 comments1 min readLW link

Notice When People Are Directionally Correct

Chris_LeongJan 14, 2024, 2:12 PM

136 points

8 comments2 min readLW link

Are Metaculus AI Timelines Inconsistent?

Chris_LeongJan 2, 2024, 6:47 AM

17 points

7 comments2 min readLW link

Random Musings on Theory of Impact for Activation Vectors

Chris_LeongDec 7, 2023, 1:07 PM

8 points

0 comments1 min readLW link

Goodhart’s Law Example: Training Verifiers to Solve Math Word Problems

Chris_LeongNov 25, 2023, 12:53 AM

27 points

2 comments1 min readLW link

(arxiv.org)

Upcoming Feedback Opportunity on Dual-Use Foundation Models

Chris_LeongNov 2, 2023, 4:28 AM

3 points

0 comments1 min readLW link

On Having No Clue

Chris_LeongNov 1, 2023, 1:36 AM

20 points

11 comments1 min readLW link

Is Yann LeCun strawmanning AI x-risks?

Chris_LeongOct 19, 2023, 11:35 AM

26 points

4 comments1 min readLW link

Don’t Dismiss Simple Alignment Approaches

Chris_LeongOct 7, 2023, 12:35 AM

137 points

9 comments4 min readLW link

[Question] What evidence is there of LLM’s containing world models?

Chris_LeongOct 4, 2023, 2:33 PM

17 points

17 comments1 min readLW link

The Role of Groups in the Progression of Human Understanding

Chris_LeongSep 27, 2023, 3:09 PM

11 points

0 comments2 min readLW link

The Flow-Through Fallacy

Chris_LeongSep 13, 2023, 4:28 AM

21 points

7 comments1 min readLW link

Chariots of Philosophical Fire

Chris_LeongAug 26, 2023, 12:52 AM

12 points

0 comments1 min readLW link

(l.facebook.com)

Call for Papers on Global AI Governance from the UN

Chris_LeongAug 20, 2023, 8:56 AM

19 points

0 comments LW link

(www.linkedin.com)

Yann LeCun on AGI and AI Safety

Chris_LeongAug 6, 2023, 9:56 PM

37 points

13 comments1 min readLW link

(drive.google.com)

A Naive Proposal for Constructing Interpretable AI

Chris_LeongAug 5, 2023, 10:32 AM

18 points

6 comments2 min readLW link