when will we have sufficiently conclusive evidence for the long term safety of far-uvc that it's reasonable to push for its universal adoption in all public spaces without reservation? the safety issue seems like a much bigger deal than the cost issue for broad adoption; if it works safely, the economic case for installing far uvc in public spaces seems pretty solid - people being sick must be terrible for the economy! and they're only ever going to get cheaper. in a world where far uvc is near universally deployed, we might be able to banish the common cold or the flu to the past, in the same way that cholera is basically no longer a problem in the developed world. this seems like a pretty big deal and I'd like to know when this glorious future is coming (and whether there's anything I can do to make it come sooner)! (from eyeballing studies, it sounds like the cost of the cold+flu to the US economy is on the order of $100bn/yr, which passes basic Fermi estimate muster - given a $30tn/yr gdp, a few days per year of lost productivity due to cold/flu is easily hundreds of billions. even at the current price of far uvc, which is a huge overestimate of future tech at volume, the cost of disinfecting spaces is about $0.40/year/sqft (amortizing an aerolamp over its 5 year lifespan); compared to e.g $60/year/sqft land cost in San Francisco, this is a negligible amount. estimating the total number of sqft of public space in the US is kind of annoying, but here's a Fermi estimate: there are about 100k schools in the US, and each school is about 100k sqft. and let's say schools are about 10% of all public spaces. that pencils out to $100bn/year, implying we are already close to break even, despite the immaturity of the technology.)

Teachers should remember their confusions. During my own studies I have noticed a lot of times, that teachers do not understand the questions from student. And this student->teacher information propagation fails as frequently as the teacher->student, and that is teacher's fault, since student can be quite articulate and still not hear the correct answer. I always had an itch to answer myself, because my level of knowledge was closer to my classmates: I can feel where they have a gap, what the teacher omissed, or divergence in their thinking process (where the person could build a different model in his mind, which is still describable by the same words). But a teacher, having 20+years of experience, have their neural patterns "optimised". Everything that is not describing the phenomenon itself gets deleted. They would not be able to recollect what aspects caused them confusion when they started. Thus they fail to comprehend the student's question and fall back to mapping the question into What they think is a reasonable question (like if it was asked on a conference) and repeating the last paragraph of their lectire, sometimes being annoyed that "students don't pay attention". And students in this corrupted situation subconciously learn that "nothing is supposed to make sense here", and they just memorise the answer. I have overheard many times how students were using different mnemonics as an explanation of the concept instead of logic/visualisation/process/reasoning. Simplified example follows:  - Why does the wing starts pitching up in this situation?  - Because buttefly. (points into a graphic that resembles butterfly, and the talk finishes, since the first student is also used to not hearing a meaningful response. He will just pass the butterfly forward, memorising some associated paragraph of dull text and numbers to spit out on the exam, without actually ever visualising pressure, streamlines, forces directions, leverage, etc) This semester I was teacher'

I'm noticing evidence that many of us may have an inaccurate view of the 1983 Soviet nuclear false alarm. I say this after reading "Did Stanislav Petrov save the world in 1983? It's complicated". The article is worth reading; it is a clear and detailed ~1100 words. I've included some excerpts here: I haven't made a thorough assessment myself. For now, I'm adding The Dead Hand to my reading list. Edited on 2025-12-25 to improve clarity of the first point. Thanks to readers for the feedback.

LLMs (and probably most NNs) have lots of meaningfull, interpretable linear feature directions. These can be found though various unsupervised methods (e.g. SAEs) and supervised methods (e.g. linear probs). However, most human interpretable features, are not what I would call the models true features. If you find the true features, the network should look sparse and modular, up to noise factors. If you find the true network decomposition, than removing the what's left over should imporve performance, not make it wors. Because the network has a limited number of orthogonal directions, there will be interference terms that the network would like to remove, but can't. A real network decomposition will be everything except this noise. This is what I think mech-interp should be looking for It's possible that I'm wrong and there is no such thing as "the networks true features". But we've (humans colectivly) only just started this reaserch agenda. The fact that we haven't found it yet, is not much evidence either way.

https://exopriors.com/embedding-atlas cool little visual treat, was too easy to whip up

My impression (primarily from former representative Justin Amash) is that individual congresspeople have almost no power. Bills are crafted and introduced at the party level, and your choices are to vote with them or not. If you don't vote with the party and are in a safe district (which most are), the party will support candidates who will go along with the party line in the primary. The only scenario in which an individual congressperson has power is a close vote in a contested district where the party can't take the risk of a primary challenger. First, I want to know if which parts of this are true, and in more detail. One guy tweeting does not constitute proof. Are elected officials sitting around watching Netflix all day, or do they still have the power to privately horse trade to support their goals. Second, assuming it is true, where did the power go? Parties aren't real, the power must be in specific humans or incentive systems. Does it all rest in the top three elected officials of each party? Their staff? Unelected party officers? I'm very interested in evidence and arguments in either direction. 

As I was looking through possible donation opportunities, I noticed that MIRI's 2025 Fundraiser has a total of only $547,024 at the moment of writing (out of the target $6M, and stretch target of $10M). Their fundraising will stop at midnight on Dec 31, 2025. At their current rate they will definitely not come anywhere close to their target, though it seems likely to me that donations will become more frequent towards the end of the year. Anyone know why they currently seem to struggle to get close to their target?