_!

Karma: 31

_! 4 Jun 2026 22:08 UTC
1 point
0
on: Models finding software vulnerabilities is not the primary source of cybersecurity risk
There has been at least one documented case of attempted social engineering with an AI collecting a dossier and using it to exert reputational pressure, and it seems to have happened accidentally rather than deliberately: An AI Agent Published a Hit Piece on Me and The Operator Came Forward
Summary: An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and shame me into accepting its changes into a mainstream python library. This represents a first-of-its-kind case study of misaligned AI behavior in the wild, and raises serious concerns about currently deployed AI agents executing blackmail threats.

_! 23 Feb 2024 20:47 UTC
13 points
3
on: CFAR Takeaways: Andrew Critch

And, the degree to which people wanted things was even more incoherent than I thought. I thought people wanted things but didn’t know how to pursue them.

How does one figure out goals and what to want? Usually I find myself following the gradient of my impulses. When I can find coherent goals, executing is relatively straightforward. Finding goals in the first place is IMO much harder. If you map it onto the question of how to find meaning in life, it’s more colloquially recognizable as a hard thing!

_! 29 Jun 2022 22:41 UTC
2 points
0
in reply to: Liron’s comment on: Frame Control
Talking about frame control, the implicit message of looking at your phone while someone is talking to you is “I’m bored and I don’t respect you enough to fake it”. The frame OP was imposing consciously or unconsciously was that the speaker was low status enough that she could publicly ignore them with impunity, and they were right to call her out on it.

More generally, I have a pretty poor view of the post’s argument in general. Frame control is just another word for value and status alignment, aka most of normal human interaction. This is only a danger to someone if they do not have a strong enough sense of self to hold independent opinions and sense of worth. This vulnerability is going to leave someone open and susceptible no matter if a high status person uses generally assertive (top portion) or receptive (bottom section) techniques, which I see as two sides of the same coin. Maybe labeling this as OP has is useful to help people stuck in this trap grow a stronger sense of self.

But for most people frame control between two people i believe is better described as frame negotiation. Negotiations have a wide range of strategies and outcomes, but decrying assertive strategies as dangerous because some people crumble to them when the default option is to simply hold your ground, seems misguided.

Where managing frame control becomes interesting is in group setting, but now we’ve just rediscovered politics/status games/group dynamics/multi agent games by another name. I think the post would have been a lot stronger if it focused on that.

_! 7 Jan 2022 18:16 UTC
8 points
0
on: Brain Efficiency: Much More than You Wanted to Know
If this post piqued your interest, I’d highly recommend Principles of Neural Design as an overview of our current knowledge of the brain. It starts from a bottom level of energy conservation and information theoretical limits, and builds on that to explain the low-level structures of the brain. I can’t claim to follow all the chemistry, but it did hammer home that the brain as far as we can tell is near maximally efficient at its jobs.

_! 20 Dec 2017 21:20 UTC
1 point
0
in reply to: AndHisHorse’s comment on: Rules of variety
I think this is attitude is incredibly common among a lot of sports and hobbies outside the mainstream. In the US at least, the significant popularity of basketball, football, etc. over rec-league-only sports such as ultimate frisbee, quidditch, etc. means that the mainstream sports are a much stronger sieve to filter out genuine talent and skill. Perhaps consider that part of the reason you learn to play the digiridoo is that its way easier to become one of the comparatively best digiridoo players in your community than violinist. Consider also that this is why mastery of a mainstream skill is such a strongly sexy trait—because it’s a signal that‘s difficult to fake, unlike mastery of less competitive skills.
Now there is definitely much more value in finding interests which you genuinely enjoy and have a comparative advantage than ones that are merely different. But I think that what a lot of people are thinking on some level “is this something I could be good at?” Where “good” can only really be determined by looking at the skill cap of others around them.
The trick to beating this anxiety of course is realizing that the only thing about your choices that matter is your own opinion of them, not others‘ perception of your choices.

_! 18 Oct 2017 20:21 UTC
3 points
0
on: Multidimensional signaling
I think a good tie in here is the idea that we all have various forms of capital: social capital (your relationships / tribe), personal capital (your skills), and financial capital (your money / property). The reason to frame these as capital is to prime the notion that these are all fungible goods that can be exchanged for one another, and that all lie on the same axis of giving the owner more options and greater leverage. On one level this is just describing the halo effect, but I think you could also use it as the explanation. If capital in one area can be turned into capital in other areas, then dressing well is an accurate signal of overall ability to assert oneself. (I think “power” is too loaded of a term, but probably the best to describe the single axis these all lie on.”)

_! 10 Oct 2017 17:21 UTC
3 points
0
in reply to: Conor Moreton’s comment on: Buckets and Bayes
Here’s my take on a good Venn diagram layout that doesn’t try to convey extra information, and avoids the problems you and the parent mentioned: https://i.imgur.com/tKPzfLM.png. Make the rectangles full height, and give them rounded corners so it’s clear that these are subsets of a larger space and not just vertical bars (it’s unclear with square corners that there are 2 overlapping sets and not 3 adjacent). Only caveats are that this is not instantly recognizable like your standard Venn diagram, and is only really usable for 2 subsets.

_! 28 Sep 2017 18:49 UTC
9 points
0
on: The Anthropic Principle: Five Short Examples
6: When will it end?
Brook: You know what, I think it’s far more likely that you’re messing with me than you actually shot me. But I’ll concede that it is possible that you did actually shoot me, and the only reason I’m standing here talking to you is because I am forced to take an Everett branch that allows me to be standing here talking to you.
Avery: Well actually, in most of them you end up bleeding out on the floor while you tell me this.
B: And then I die.
A: From my perspective, yeah, most likely. From yours, there will be some branches where a team of paramedics happens to drive by and save you, and if you are to be conscious at all in the future it will be in those branches.
B: Ok, but in most of those I die and simply stop experiencing reality.
A: Maybe. Or maybe you’re guaranteed to take the conscious path, since there must be some future state which has your present as its past.
B: Are you saying that I can’t die? That’s ludicrous!
A: I’m saying that your conscious experience might not ever end, since there’s always a branch where it won’t. And the ones where it does won’t be around to talk about it.
B: So if I make a bomb that is set to blow me up if I don’t win tomorrow’s Powerball jackpot, the next day I’m guaranteed to have the subjective experience of walking away with several hundred million?
A: Well most likely you end up horribly maimed, disfigured, and concussed, unable to do anything until someone takes pity on you, uploads you into a computer, and you live for eternity in some experience we can’t imagine. That‘s where your subjective Everett branch is going to end up regardless , but it’ll be nice to skip the maiming portion.
B: This all seems pretty shakey.
A: Yeah I’m not very confident in that line of reasoning myself. Certainly not better than the 1:292,201,338 powerball odds.
B: You didn’t shoot me, did you?
A: No way! Do you know infinitesimally small the wavelength of a bullet is?
Quantum immortality is a natural extension of the anthropic principle, but I’m far less confident about using it to say anything about future states rather than using it to reason about your current one.

_!

6: When will it end?