Humans are really good at moving in space. We do motor planning and especially error correction much better than existing robot control systems. Could a transformer model trained on a large library of annotated human movement data serve as a controller for a humanoid robot or robotic limb? My impression...
There was a recent contest that got promoted on lesswrong offering pieces of a 20K prize for one-liners and short-forms for convincing folks that AGI alignment is important. I'm too late for the money, but this is my (thousand times longer than requested) contribution. Background Eliezer recently wrote "AGI Ruin:...
Took me a while to get back to this question. I didn't know the answer so I looked up some papers. The short answer is, knowing this requires long follow-up periods which studies are generally not good at so we don't have great answers. Definitely a significant number of people don't stay better.
The longer answer is, probably about half of people need some form of maintenance treatment to stay non-depressed for more than a year, but our view of this is very confounded. Some studies have used normal antidepressant medications for maintenance, and some studies have tried additional rounds of TMS, both of which work really well. Up to a third of... (read more)
Hi Sable, I'm a TMS (+EEG) researcher. I'm happy to see some TMS discussed here and this is a nice introductory writeup. If you had any specific questions about TMS or the therapy I'd be happy to answer them or point you in the right direction. Depression is not my personal area of study or expertise, but it's hard not to know a lot about depression treatment if you study TMS for a living because it's the most successful application of the technique.
Two specific things you mentioned - first, that TMS depression therapy does not require or use an MRI. It's right of you to point this out, because doesn't it seem... (read more)
Humans are really good at moving in space. We do motor planning and especially error correction much better than existing robot control systems.
Could a transformer model trained on a large library of annotated human movement data serve as a controller for a humanoid robot or robotic limb? My impression is that a movement model might not be useful for directly controlling servos, because human and robot bodies are so different. But perhaps it could improve the motor planning and error correction layer?
The data would presumably take the form of a 3D wireframe model of the limb/body and its trajectory through space, the goal of the movement ("pour water from this cup to that cup") and some rating of success or failure.
I don't have experience in either LLMs/transformer models or robotics so this question might miss some obvious points, but I couldn't get the idea out of my head!
Wanted to say that I enjoyed this and found it much more enlightening than I expected to, given that I have no intrinsic interest in dentistry. I would value a large cross-discipline sample of this question set and think it would have been very useful to my younger self. I think the advice millennials were given when considering college degrees and careers was generally unhelpful magical thinking. These practical questions are helpful. I'd be interested in slightly longer form answers. Are these edited, or was this interviewee laconic?
Yes, the notion of being superceded does disturb me. Not in principle, but pragmatically. I read your point, broadly, to be that there are a lot of interesting potential non-depressing outcomes to AI, up to advocating for a level of comfort with the idea of getting replaced by something "better" and bigger than ourselves. I generally agree with this! However, I'm less sanguine than you that AI will "replicate" to evolve consciousness that leads to one of these non-depressing outcomes. There's no guarantee we get to be subsumed, cyborged, or even superceded. The default outcome is that we get erased by an unconscious machine that tiles the universe with smiley faces and keeps that as its value function until heat death. Or it's at least a very plausible outcome we need to react to. So caring about the points you noted you care about, in my view, translates to caring about alignment and control.
"For example, if I were making replicators, I'd ensure they were faithful replicators "
Isn't this the whole danger of unaligned AI? It's intelligent, it "replicates" and it doesn't do what you want.
Besides physics-breaking 6, I think the only tenuous link in the chain is 5; that AI ("replicators") will want to convert everything to comptronium. But that seems like at least a plausible value function, right? That's basically what we are trying to do. It's either that or paperclips, I'd expect.
(Note, applaud your commenting to explain downvote.)
While I may or may not agree with your more fantastical conclusions, I don't understand the downvotes. The analogy between biological, neural, and AI systems is not new but is well presented. I particularly enjoyed the analogy that comptronium is "habitable space" to AI. Minus physics-as-we-know-it breaking steps, which are polemic and not crucial to the argument's point, I'd call on downvoters to be explicit about what they disagree with or find unhelpful.
Speculatively, perhaps at least some find the presentation of AI as the "next stage of evolution" infohazardous. I'd disagree. I think it should start discussion along the lines of "what we mean by alignment". What's the end state for a human society with "aligned" AI? It probably looks pretty alien to our present society. It probably tends towards deep machine mediated communication blurring the lines between individuals. I think it's valuable to envision these futures.
Netcentrica, in this letter your explicit opinion is that fiction with a deep treatment of the alignment problem will not be palatable to a wider audience. I think this is not necessarily true. I think that compelling fiction is perhaps the prime vector for engaging a wider, naive audience. Even the Hollywood treatment of I Robot touched on it and was popular. Not deep or nuanced, sure. But it was there. Maybe more intelligent treatments could succeed if produced with talent.
I mostly stopped reading sci Fi after the era of Asimov and Bradbury. I'd be interested in comments on which modern, popular authors have written or produced AI fiction with the most intelligent treatment of the assignment issue (or related issues), to establish a baseline.
Hmm, yeah, I guess that's a good point. I was thinking myopically at a systems level. The post is useful advice for a patient who is willing to do their own research, confident they can do it thoroughly, and is not afraid to "stare into the abyss" i.e risk getting freaked out or overwhelmed.
Although, I also wonder if insurance companies might try to exploit a patient's prior decision to decline recommended treatment/tests as a reason to not cover future costs...
.
I don't disagree with you exactly, but I think the focus on rational decision making misses the context the decisions are being made in. Isn't this just an unaligned incentives problem? When a patient complains of an issue, doctors face exposure to liability if they do not recommend tests to clarify the issue. If the tests indicate something, doctors face liability for not recommending corrective procedures. They generally face less liability for positively recommending tests and procedures because the risk is quantifiable beforehand and the patient makes the decision. If they decline a recommended test, the doctor can't be blamed.
The push to do less testing makes sense in that context. It has... (read more)
There was a recent contest that got promoted on lesswrong offering pieces of a 20K prize for one-liners and short-forms for convincing folks that AGI alignment is important. I'm too late for the money, but this is my (thousand times longer than requested) contribution.
Eliezer recently wrote "AGI Ruin: A List of Lethalities” which included a fairly sci-fi scenario about how an unaligned AGI might go about killing everyone. I noticed that I found this both novel and poorly framed.
I found it novel because alignment discussions I've read are usually exceptionally handwavy about how an unaligned AGI would attack. So I appreciated that Eliezer went a little deeper into it. However, I found... (read 2843 more words →)
Hey, I remember your medical miracle post. I enjoyed it!
"Objectively" for me would translate to "biomarker" i.e., a bio-physical signal that predicts a clinical outcome. Note that for depression and many psychological issues this means that we find the biomarkers by asking people how they feel...but maybe this is ok because we do huge studies with good controls, and the biomarkers may take on a life of their own after they are identified.
I'm assuming you mean biomarkers for psychological / mental health outcomes specifically. This is spiritually pretty close to what my lab studies - ways to predict how TMS will affect individuals, and adjust it to make it work better in... (read more)