LESSWRONG
LW

Alan E Dunne
163160
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
2Alan E Dunne's Shortform
4mo
1
No wikitag contributions to display.
Alan E Dunne's Shortform
Alan E Dunne4mo-20

On catastrophic risk and effective persuasion:

https://us06web.zoom.us/webinar/register/WN_j555baQqRjeWhiefEAQ82Q#/registration

Reply
My Current Thoughts on the AI Strategic Landscape
Alan E Dunne2y10

So far as the slave carries out immediate work from fear of consequences they are locally aligned with the master's will.

Reply
Public Opinion on AI Safety: AIMS 2023 and 2021 Summary
Alan E Dunne2y10

How did you get respondents? Why are they "nationally representative"?

Reply
What is to be done? (About the profit motive)
Alan E Dunne2y10

1/ evidence for these statements?

2/ in what sense is it profitable to throw away food or maintain empty dwellings that is distinct from "maintaining everyone else's quality of life"?

3/ if the evil is that some people's needs are not valued enough could that not be remedied by giving them money and making it profitable to meet their needs?

Reply
Polarization is Not (Standard) Bayesian
Alan E Dunne2y21

Is martingale different from conservation of expected evidence?

https://www.lesswrong.com/posts/jiBFC7DcCrZjGmZnJ/conservation-of-expected-evidence

Reply
Evaluating GPT-4 Theory of Mind Capabilities
Alan E Dunne2y30

With Respect

       Given that in more than a third of the cases where GPT and the answer set disagreed you thought GPT was right and the answer set was wrong, did you check for cases where GPT and the answer set agreed on an answer you thought was wrong?

    Yours Sincerely

Reply
Review & rebuttal of "Why machines will never rule the world: artificial intelligence without fear"
Answer by Alan E DunneJul 08, 202370

Astral Codex Ten: https://astralcodexten.substack.com/p/your-book-review-why-machines-will

Reply
What are the best non-LW places to read on alignment progress?
Alan E Dunne2y21

This seems to have stopped in July 2022.

Reply
[Linkpost] Introducing Superalignment
Alan E Dunne2y30

"Finally, we can test our entire pipeline by deliberately training misaligned models, and confirming that our techniques detect the worst kinds of misalignments (adversarial testing)."

Reply
Idea: medical hypotheses app for mysterious chronic illnesses
Alan E Dunne2y10

In a "heatplot" or plots cf https://www.elsblog.org/the_empirical_legal_studi/2023/05/heatplots-for-correlation-coefficients-graphs.html

Reply
Load More
2Alan E Dunne's Shortform
4mo
1
-1Evaluation Evidence Reconstructions of Mock Crimes Submission 3
2y
0
-1Evaluating Evidence Reconstructions of Mock Crimes -Submission 2
2y
1
1Evaluating Evidence Reconstructions of Mock Crimes
Q
2y
Q
0