LESSWRONG
LW

JMiller
25681030
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
PSA: The LessWrong Feedback Service
JMiller2mo83

This is really cool, and the PSA was helpful since I had no idea. Kudos to you and the LW team!

Reply
Training AGI in Secret would be Unsafe and Unethical
JMiller3mo21

Great post, Daniel! 

I would expect that a misaligned ASI of the first kind would seek to keep knowledge of its capabilities to a minimum while it accumulates power. If nothing else, because by definition it prevents the detection and mitigation of its misalignment. Therefore for the same reasons this post advocates for openness past a certain stage of development, the unaligned ASI of the first kind would move towards a concentration and curtailing of knowledge (I.e. it would not be the kind of AI that stops the finding and fixing of its misalignment if it allowed 10x-1000x more human brain power investigating itself).


One way to increase the likelihood of keeping itself hidden is by influencing the people that already possess knowledge of its capabilities to act toward that outcome. So even if the few original decision makers with knowledge and power are predisposed to eventual openness/benevolence, the ASI could (rather easily, I imagine) tempt them away from said policy. Moreover, it could help them mitigate, reneg on,  neutralize or ignore any precommitments or promises previously made in favour of openness. 


 

Reply
Power Lies Trembling: a three-book review
JMiller3mo10

I really enjoyed this post, Richard! The object level message is inspiring, but I also found myself happily surprised at the synthesis of three books which, on their surface, are about quite different subjects! Just throwing my +1 here as someone interested in reading more posts like this. 

 

Reply
Why White-Box Redteaming Makes Me Feel Weird
JMiller4mo60

I definitely agree with this last point! I've been on the providing end of similar situations with people in cybersecurity education of all sorts of different technical backgrounds. I've noticed that both the tester and the "testee" (so to speak) tend to have a better and safer experience when the cards are compassionately laid out on the table at the end. It's even better when the tester is able to genuinely express gratitude toward the testee for having taught them something new, even unintentionally. 

Reply
How I've run major projects
JMiller4mo31

Hey Ben, thanks for this! I especially appreciate the section on Slack norms; I've found that teams have a tendency to default to DMs without explicit, mindful management of channels, channel membership and expectation-setting. 

One dynamic I've noticed: when team members get really into a conversation and it becomes a "centithread", it often benefits from outsider-nudging to remind folks that they'd be better off jumping in a call, and then summarizing the discussion. 

Reply
Best Explainers on Different Subjects
JMiller10y00

Awesome, I'll be checking this out for sure. I recently began studying computer security; do you have any more recommendations?

Reply
Best Explainers on Different Subjects
JMiller10y40

I appreciate the initiative to send meta-sources rather than single pieces.

Reply
Best Explainers on Different Subjects
JMiller10y00

Added to my reading list, thanks!

Reply
Best Explainers on Different Subjects
JMiller10y40

Thanks Gunnar. Luke may not have linked his thread, because I did so in the OP.

Reply
Best Explainers on Different Subjects
JMiller10y00

Thanks, Luke. I'll be checking your physics recommendations out soon.

Reply
Load More
19Best Explainers on Different Subjects
10y
24
7Rewiring my Brain: (gentle) Help Appreciated
12y
48
0Computer Science and Software Engineering
12y
30
10Confusion about Normative Morality
12y
103
32[suggestion] New Meetup Tab
12y
4
2Morality: Theory and Practice
12y
22
2A question about two books concerning biases
12y
8
3A Probability Question
13y
16