Posts

Evaluation Evidence Reconstructions of Mock Crimes Submission 3 2023-05-31T19:03:30.320Z
Evaluating Evidence Reconstructions of Mock Crimes -Submission 2 2023-05-24T22:17:56.037Z
Evaluating Evidence Reconstructions of Mock Crimes 2023-05-21T23:27:53.259Z

Comments

Comment by Alan E Dunne on My Current Thoughts on the AI Strategic Landscape · 2023-09-29T19:59:46.450Z · LW · GW

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

Comment by Alan E Dunne on Public Opinion on AI Safety: AIMS 2023 and 2021 Summary · 2023-09-25T19:42:31.317Z · LW · GW

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

Comment by Alan E Dunne on What is to be done? (About the profit motive) · 2023-09-24T17:11:04.290Z · LW · GW

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?

Comment by Alan E Dunne on Polarization is Not (Standard) Bayesian · 2023-09-17T18:26:14.080Z · LW · GW

Is martingale different from conservation of expected evidence?

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

Comment by Alan E Dunne on Evaluating GPT-4 Theory of Mind Capabilities · 2023-08-10T20:58:29.336Z · LW · GW

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

Comment by Alan E Dunne on Review & rebuttal of "Why machines will never rule the world: artificial intelligence without fear" · 2023-07-08T20:34:33.160Z · LW · GW

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

Comment by Alan E Dunne on What are the best non-LW places to read on alignment progress? · 2023-07-07T16:23:07.214Z · LW · GW

This seems to have stopped in July 2022.

Comment by Alan E Dunne on [Linkpost] Introducing Superalignment · 2023-07-05T22:02:55.669Z · LW · GW

"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)."

Comment by Alan E Dunne on Idea: medical hypotheses app for mysterious chronic illnesses · 2023-06-23T18:06:41.358Z · LW · GW

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

Comment by Alan E Dunne on Idea: medical hypotheses app for mysterious chronic illnesses · 2023-06-23T18:02:25.303Z · LW · GW

You could also study the distribution of correlation strengths found over the range of correlations tested, possible, seeing how it compares to what would be expected by chance.

Comment by Alan E Dunne on Andrew Ng wants to have a conversation about extinction risk from AI · 2023-06-12T01:39:42.971Z · LW · GW

https://www.lesswrong.com/posts/QzkTfj4HGpLEdNjXX/an-artificially-structured-argument-for-expecting-agi-ruin

Comment by Alan E Dunne on Statement on AI Extinction - Signed by AGI Labs, Top Academics, and Many Other Notable Figures · 2023-05-31T21:25:37.305Z · LW · GW

skeptical reaction with one expression of support: https://statmodeling.stat.columbia.edu/2023/05/31/jurassic-ai-extinction/

Comment by Alan E Dunne on Book Review: How Minds Change · 2023-05-26T14:25:07.161Z · LW · GW

https://statmodeling.stat.columbia.edu/2015/12/16/lacour-and-green-1-this-american-life-0/

 

and generally "beware the one of just one study"

Comment by Alan E Dunne on Science in a High-Dimensional World · 2023-05-25T18:46:42.373Z · LW · GW

In 26 models taken from volumes 21 to 25 of the journal Law and Human Behavior, the highest R-squared -proportion of VARIANCE, not variation, explained was  40% and the  second highest 24%

Comment by Alan E Dunne on What fact that you know is true but most people aren't ready to accept it? · 2023-05-21T16:58:41.120Z · LW · GW

Evidence?