All Posts

Sorted by Magic (New & Upvoted)

Thursday, June 8th 2023
Thu, Jun 8th 2023

AI 10
Practical 3
World Modeling 2
Evolution 2
Exercise (Physical) 1
Health / Medicine / Disease 1
More
Frontpage Posts
Shortform
11Czynski8d
The 'new user' flag being applied to old users with low karma is condescending as fuck. I'm not a new user. I'm an old user who has spent most of my recent time on LW telling people things they don't want to hear. Well, most of the time I've actually spent posting weekly meetups, but other than that.
4
5Garrett Baker8d
Last night I had a horrible dream: That I had posted to LessWrong a post filled with useless & meaningless jargon without noticing what I was doing, then I went to slee, and when I woke up I found I had <−60 karma on the post. When I read the post myself I noticed how meaningless the jargon was, and I myself couldn't resist giving it a strong-downvote.
5DirectedEvolution8d
Over the last six months, I've grown more comfortable writing posts that I know will be downvoted. It's still frustrating. But I used to feel intensely anxious when it happened, and now, it's mostly just a mild annoyance. The more you're able to publish your independent observations, without worrying about whether others will disagree, the better it is for community epistemics.
1
3jacquesthibs8d
AI labs should be dedicating a lot more effort into using AI for cybersecurity as a way to prevent weights or insights from being stolen. Would be good for safety and it seems like it could be a pretty big cash cow too. If they have access to the best models (or specialized), it may be highly beneficial for them to plug them in immediately to help with cybersecurity (perhaps even including noticing suspicious activity from employees). I don’t know much about cybersecurity so I’d be curious to hear from someone who does.
3Quinn8d
messy, jotting down notes: * I saw this thread https://twitter.com/alexschbrt/status/1666114027305725953 [https://twitter.com/alexschbrt/status/1666114027305725953] which my housemate had been warning me about for years. * failure mode can be understood as trying to aristotle the problem, lack of experimentation * thinking about the nanotech ASI threat model, where it solves nanotech overnight and deploys adversarial proteins in all the bloodstreams of all the lifeforms. * These are sometimes justified by Drexler's inside view of boundary conditions and physical limits. * But to dodge the aristotle problem, there would have to be an amount of bandwidth of what's passing between sensors and actuators (which may roughly correspond to the number of do applications in pearl) * Can you use something like communication complexity https://en.wikipedia.org/wiki/Communication_complexity [https://en.wikipedia.org/wiki/Communication_complexity] (between a system and an environment) to think about "lower bound on the number of sensor-actuator actions" mixed with sample complexity (statistical learning theory) * Like ok if you're simulating all of physics you can aristotle nanotech, for a sufficient definition of "all" that you would run up against realizability problems and cost way more than you actually need to spend. Like I'm thinking if there's a kind of complexity theory of pearl (number of do applications needed to acquire some kind of "loss"), then you could direct that at something like "nanotech projects" to fermstimate the way AIs might tradeoff between applying aristotlean effort (observation and induction with no experiment) and spending sensor-actuator interactions (with the world). There's a scenario in the sequences if I recall correctly about which physics an AI infers from 3 frames of a video of an apple falling, and something about how security mindset suggests you shouldn't expect your information-theoret