Independent alignment researcher
I have signed no contracts or agreements whose existence I cannot mention.
Garrett Baker
Karma: 4,514
An effect I noticed: Going through Aella’s correlation matrix (with poorly labeled columns sadly), a feature which strongly correlates with the length of a relationship is codependency. Plotting question
20. "The long-term routines and structure of my life are intertwined with my partner's" (li0toxk)assuming that’s what “codependency” refers toThe shaded region is a 95% posterior estimate for the mean of the distribution conditioned on the time-range (every 2 years) and cis-male respondents, with prior .
Note also that codependency and sex satisfaction are basically uncorrelated
This shouldn’t be that surprising. Of course the longer two people are together the more their long term routines will be caught up with each other. But also this seems like a very reasonable candidate for why people will stick together even without a good sex life.
This seems right as a criticism, but this seems better placed on the EA forum. I can’t remember the last time I heard anyone talking about ITN on LessWrong. There are many considerations ITN leaves out, which should be unsurprising given how simplified it is.
So, the recipe for making a broken science you can’t trust is
The public cares a lot about answers to questions that fall within the science’s domain.
The science currently has no good attack angles on those questions.
To return to LessWrong’s favorite topic, this doesn’t bode well for alignment.
I understand the argument, I think I buy a limited version of it (and also want to acknowledge that it is very clever and I do like it), but I also don’t think this can explain the magnitude of the difference between the different fields. If we go back and ask “what was physics’ original goal?” we end up with “to explain how the heavens move, and the path that objects travel”, and this has basically been solved. Physicists didn’t substitute this for something easier. The next big problem was to explain heat & electricity, and that was solved. Then the internals of the atom, and the paradox of a fixed speed of light. And those were solved.
I think maybe your argument holds for individual researchers. Individual education researchers are perhaps more constrained in what their colleagues will be interested in than individual physicists (though even that I’m somewhat doubtful of, maybe less doubtful on the scale of labs). But it seems to definitely break down when comparing the two fields against each other. Then, physics clearly has a very good track record of asking questions and then solving them extraordinarily well.
I will also note that Aella’s relationships data is public, and has the following questions:
1. Your age? (rkkox57) 2. Which category fits you best? (4790ydl) 3. In a world where your partner was fully aware and deeply okay with it, how much would you be interested in having sexual/romantic experiences with people besides your partner? (ao3mcdk) 4. In a world where you were fully aware and deeply okay with it, how much would *your partner* be interested in having sexual/romantic experiences with people besides you? (wcq3vrx) 5. To get a little more specific, how long have you been in a relationship with this person? (wqx272y) 6. Which category fits your partner best? (u9jccbo) 7. Are you married to your partner? (pfqs9ad) 8. Do you have children with your partner? (qgjf1nu) 9. Have you or your partner ever cheated on each other? (hhf9b8h) 10. On average, over the last six months, about how often do you watch porn or consume erotic content for the purposes of arousal? (vnw3xxz) 11. How often do you and your partner have a fight? (x6jw4sp) 12. "It’s hard to imagine being happy without this relationship." (6u0bje) 13. "I have no secrets from my partner" (bgassjt) 14. "If my partner and I ever split up, it would be a logistical nightmare (e.g., separating house, friends) (e1claef) 15. "If my relationship ended I would be absolutely devastated" (2ytl03s) 16. "I don't really worry about other attractive people gaining too much of my partner's affection" (61m55wv) 17. "I sometimes worry that my partner will leave me for someone better" (xkjzgym) 18. "My relationship is playful" (w2uykq1) 19. "My partner an I are politically aligned" (12ycrs5) 20. "We have compatible humor" (o9empfe) 21. "The long-term routines and structure of my life are intertwined with my partner's" (li0toxk) 22. "The passion in this relationship is deeply intense" (gwzrhth) 23. "I share the same hobbies with my partner" (89hl8ys) 24. "My relationship causes me grief or sorrow" (rm0dtr6) 25. "If we broke up, I think I could date a higher quality person than they could" (vh27ywp) 26. "In hindsight, getting into this relationship was a bad idea" (1y6wfih) 27. "I feel like I would still be a desirable mate even if my partner left me" (qboob7y) 28. "My partner and I are sexually compatible" (9nxbebp) 29. "I often feel jealousy in my relationship" (kfcicm9) 30. "I think this relationship will last for a very long time" (ob8595u) 31. "My partner enables me to learn and grow" (e2oy448) 32. "My partner doesn't excite me" (6fcm06c) 33. "My partner doesn't sexually fulfill me" (xxf5wfc) 34. "I rely on my partner for a sense of self worth" (j0nv7n9) 35. "My partner and I handle fights well" (brtsa94) 36. "I feel confident in my relationship's ability to withstand everything life has to throw at us" (p81ekto) 37. "I sometimes fear my partner" (a21v31h) 38. "I try to stay aware of my partner's potential infidelity" (5qbgizc) 39. "I share my thoughts and opinions with my partner" (6lwugp9) 40. "This relationship is good for me" (wko8n8m) 41. "My partner takes priority over everything else in my life" (2sslsr1) 42. "We respect each other" (c39vvrk) 43. "My partner is more concerned with being right than with getting along" (rlkw670) 44. "I am more needy than my partner" (f3or362) 45. "I feel emotionally safe with my partner" (or9gg0a) 46. "I'm satisfied with our sex life" (6g14ks) 47. "My partner physically desires me" (kh7ppyp) 48. "My partner and I feel comfortable explicitly discussing our relationship on a meta level" (jrzzb06) 49. "My partner knows all my sexual fantasies" (s3cgjd2) 50. "My partner and I are intellectually matched" (ku1vm67) 51. "I am careful to maintain a personal identity separate from my partner" (u5esujt) 52. "I'm worried I'm not good enough for my partner" (45rohqq) 53. "My partner judges me" (fr4mr4a) 54. Did you answer this survey honestly/for a real partner? (7bfie2v) 55. On average, over the last six months, about how often do you and your partner have sex? (n1iblql) 56. Is the partner you just answered for, your longest romantic relationship? (zjfk3cu)which should allow you to test a lot of your candidate answers, for example your first 3 hypotheses could be answered by looking at these:
-
Do you have children with your partner? (qgjf1nu)
-
“If my partner and I ever split up, it would be a logistical nightmare (e.g., separating house, friends) (e1claef) or 21. “The long-term routines and structure of my life are intertwined with my partner’s” (li0toxk)
-
“I feel like I would still be a desirable mate even if my partner left me” (qboob7y)
-
Historically attempts to curtail this right lead to really really dark places. Part of living in a society with rights and laws is that people will do bad things the legal system has no ability to prevent. And on net, that’s a good thing. See also.
An obvious answer you missed: Lacking a prenup, courts often rule in favor of the woman over the man in the case of a contested divorce.
I didn’t say anything about temperature prediction, and I’d also like to see any other method (intuition based or otherwise) do better than the current best mathematical models here. It seems unlikely to me that the trends in that graph will continue arbitrarily far.
Thanks for the pointer to that paper, the abstract makes me think there’s a sort of slow-acting self-reinforcing feedback loop between predictive error minimisation via improving modelling and via improving the economy itself.
Yeah, that was my claim.
Even more importantly, we only measured the AIs at software tasks and don’t know what the trend is for other domains like math or law, it could be wildly different.
You probably mention this somewhere, but I’ll ask here, are you currently researching whether these results hold for those other domains? I’m personally more interested about math than law.
It does not seem like this writer is aware of the Von Neumann–Morgenstern utility theorem. There are criticisms one can level against utility as a concept, but the central question ends up being which of those axioms do you disagree with and why? For example, Garabrant’s Geometric Rationality is a great counter if you’re looking for one.
Edit: I notice that all of your previous posts have been of this same format, and they all consistently receive negative karma. You should probably reconsider what you post to this forum.
The weather, or the behavior of any economy larger than village size, for example—systems so chaotically interdependent that exact prediction is effectively impossible (not just in fact but in principle).
Flagging that those two examples seem false. The weather is chaotic, yes, and there’s a sense in which the economy is anti-inductive, but modeling methods are advancing, and will likely find more loop-holes in chaos theory.
For example, in thermodynamics, temperature is non-chaotic while the precise kinetic energies and locations of all particles are. A reasonable candidate similarity in weather are hurricanes.
Similarly as our understanding of the economy advances it will get more efficient which means it will be easier to model. eg (note: I’ve only skimmed this paper). And definitely large economies are even more predictable than small villages, talk about not having a competitive market!
My model is that early on physics had very impressive & novel math, which attracted people who like math, who did more math largely with the constraint the math had to be trying to model something in the real world, which produced more impressive & novel math, which attracted more people who like math, etc etc, and this is the origin of the equilibrium.
Note a similar argument can be made for economics, though the nice math came much later on, and obviously was much less impactful than literally inventing calculus.
Happy to take your word on these things if the wikipedia article is unrepresentative!
Lighthaven Sequences Reading Group #27 (Tuesday 03/25)
In contrast, physicists were not committed to discovering the periodic table, fields or quantum wave functions. Many of the great successes of physics are answers to question no one would think to ask just decades before they were discovered. The hard sciences were formed when frontiers of highly tractable and promising theorizing opened up.
This seems a crazy comparison to make[1]. These seem like methodological constraints. Are there any actual predictions past physics was trying to make which we still can’t make and don’t even care about? None that I can think of.
- ↩︎
Since ancient greece people were trying to break things down into their elements, though of course they called it “stoikheion”, which literally means “One of a row”. Now of course, they were wrong, it turns out the stoicheia ought to be arranged in a table not a row. But in either case the idea was there. “We can break things down into their elemental units and those things will have definite interaction properties we can use to understand all substances”.
- ↩︎
Apropos of the comments below this post, many seem to be assuming humans can complete tasks which require arbitrarily many years. This doesn’t seem the case to me. People often peak intellectually in their 20′s, and sometimes get dementia late in life. Others just get dis-interested in their previous goals through a mid-life crisis or ADHD.
I don’t think this has much an impact on the conclusions reached in the comments (which is why I’m not putting this under the post), but this assumption does seem wrong in most cases (and I’d be interested in cases where people think its right!)
Capitalist Realism by Mark Fisher (as close to a self-portrait by the modern humanities as it gets)
At least reading the wikipedia, this… does not seem so self-conscious to me. Eg.
Fisher regards capitalist realism as emerging from a purposeful push by the neoliberal right to transform the attitudes of both the general population and the left towards capitalism and specifically the post-Fordist form of capitalism that prevailed throughout the 1980s. The relative inability of the political left to come up with an alternative economic model in response to the rise of neoliberal capitalism and the concurrent Reaganomics era created a vacuum that facilitated the birth of a capitalist realist perspective. The collapse of the Soviet Union, which Fisher believes represented the only real example of a working non-capitalist system, further cemented the place of capitalist realism both politically and in the general population, and was hailed as the decisive final victory of capitalism. According to Fisher, in a post-Soviet era, unchecked capitalism was able to reframe history into a capitalist narrative in which neoliberalism was the result of a natural progression of history and even embodied the culmination of human development.
and
Fisher argues that the bank bailouts following the 2008 economic crisis were a quintessential example of capitalist realism in action, reasoning that the bailouts occurred largely because the idea of allowing the banking system to fail was unimaginable to both politicians and the general population. Due to the intrinsic value of banks to the capitalist system, Fisher proposes that the influence of capitalist realism meant that such a failure was never considered an option. As a consequence, Fisher observes, the neoliberal system survived and capitalist realism was further validated. Fisher classifies the current state of capitalist realism in the neoliberal system in the following terms:
The only powerful agents influencing politicians and managers in education are business interests. It’s become far too easy to ignore workers and, partly because of this, workers feel increasingly helpless and impotent. The concerted attack on unions by neoliberal interest groups, together with the shift from a Fordist to a post-Fordist organisation of the economy – the move towards casualisation, just-in-time production, globalization – has eroded the power base of unions [and thus the labor force].
These are not exactly hard-hitting or at all novel or even interesting criticisms. And they’re not even criticisms of humanities! So how can it be self-conscious?
And we didn’t filter them in any way.
This seems contrary to what that page claims
Here, we present highly misaligned samples (misalignment >= 90) from GPT-4o models finetuned to write insecure code.
And indeed all the samples seem misaligned, which seems unlikely given the misaligned answer rate for other questions in your paper.
In my experience playing a lot with LLMs, “Nova” is a reasonably common name they give themselves if you ask, and sometimes they will spontaneously decide they are sentient, but that is the extent to which my own experiences are consistent with the story. I can imagine though that since the time I was playing with these things a lot (about 6 months ago) much has changed.
That’s a whole seven words!, most of which are a whole three syllables! There is no way a motto like that catches on.