LessWrong 2.0 Reader

Although I somewhat agree with the comment about style, I feel that the point you're making could be received with some more enthusiasm. How well-recognized is this trolley problem fallacy? The way I see it, the energy spent on thinking about the trolley problem in isolation illustrates innate human short-sightedness and perhaps a clear limit of human intelligence as well. 'Correctly' solving one trolley problem does not prevent that you or someone else will be confronted with the next. My line of arguing is that the question of ethical decision making requires an agent to also have a proper 'theory of mind': if I am making this decision, what decision will a next person or agent have to deal with? If my car with four passengers chooses to avoid running over five people to just hit one, could it also put another oncoming car in the position where they have to choose between a collision with 8 people and evading and killing 5? And of course: whose decisions resulted in the trolley problem I'm currently facing and what is their responsibility? I recently contributed a piece that is essentially about propagating consequences of decisions and I'm curious how it will be received. Could it be that this is a bit of a blind spot in ethics and/or AI safety? Given the situations we've gotten ourselves in as a society, I feel this also is an area in which humans can very easily be outsmarted...

I made a slightly improved version that adds subtitles and skips silence.

Made a slightly improved version.

Thanks for the feedback. I've added some headers to break it up.

Fundamentally, OP is making the case that Biorisk is an extremely helpful (but not exact) analogy for AI risk, in the sense that we can gain understanding by looking the ways it's analogous, and then get an even more nuanced understanding by analyzing the differences.

The point made seems to be more about it's place in the discourse than about the value of the analogy itself? (E.g. "The Biorisk analogy is over-used" would be less misleading then)

Would you please expand on how ai-plans.com addresses the question from the post above ... ?

Maybe let's try to make a smart counter-move and accelerate the development of for-profit AI Safety projects [...] ? With the obvious idea to pull some VC money, which is a different pool than AI safety philanthropic funds.

I took a look at ai-plans, but I have yet to find information about:

1. How does it work?
2. Who created it?
3. What is the motivation for building it?
4. What problem(s) will ai-plans help solve?
5. Who controls / curates / moderates it?
6. What is the process/algorithm for: curation? moderation? ranking?

I would suggest (i) answering these questions on the ai-plans website itself then (ii) adding links here.

Thanks for the question! This is not something we have included in our distribution, so I think our patching experiments aren't answering that question. If I would speculate though, I'd suggest

• The Prev Tok head 1.4 might "check" for a signature of "I am inside a function definition" (maybe a L0 head that attends to the def keyword. This would make it work only on B_def not B_dec
• Duplicate Tok head 1.2 might help the mover heads by suppressing their attention to repeated tokens. We observed this ("Duplicate Token Head 1.2 is helping Argument Movers"), but were not confident whether it is important. When doing ACDC we felt 1.2 wasn't actually too important (IIRC) but again this would depend on the distribution

In summary, I can think of a range of possible mechanisms how the model could achieve that, but our experiments don't test for that (because copying the 2nd token after B_dec would be equally bad for the clean and corrupted prompts).

I read an article about McDonalds a while ago. One of the things that powered their early success and growth was an extremely small menu. The slim menu meant that the kitchen had little variety enabling everything to be done faster and cheaper.

(https://en.wikipedia.org/wiki/History_of_McDonald%27s)

A giant company with 50 products could plausibly have 50 teams, each of which is focussed on making its product the best it can be. So the "focus" doesn't have to be lost at scale, its more like a bunch of different organisations under one umbrella.

I think it is pretty conclusive that sunscreen wearing will improve your skin complexion and smoothness in the long term (presumably the effect is not worth having if you never go outside in sunshine, obv). 

Whether it has enough material effect to do anything to your risk of dying from malignant melonoma (which is pretty rare anyway), is more of an open question. It might not be a worthwhile trade-off for everyone. 

I think the hidden motives are basically rationalisation, I have found myself singlethinking those motives in the past nowadays I just bring those reasons to the centre-stage and try to actually find whether they align with my commitments instead of motivated stopping. Sometimes I just corner my motivated reasoning (bottom line) so bad (since it's not that hard to just do expected consequentialist reasoning properly for day to day stuff) that instead of my brain trying to come up with better reasoning it just makes the idea of the impulsive action more salient, some urge along the lines of "think less and intuit/act more".  

Also I have personally used this concept of "intellectual masturbation" to divert discussions away from potentially philosophical bomb to more relevant topics it's much better to reduce the philosophical jargon in day to day conversations lol.