I've found that too. Taking $\log \left(L0\right)$ and $\log \left(MSE\right)$ both seem reasonable to me, but it feels weird to me to take $\log \left(DownstreamLoss\right)$ for cross-entropy losses, since that's already log-ish. In my case the plots were generally worse to look at than the ones I showed above when scanning over a very broad range of $L1$ coefficients (and therefore $L0$ values).

Is there a solution to avoid constraining the norms of the columns of $W_{dec}$ to be 1? Anthropic report better results when letting it be unconstrained. I've tried not constraining it and allowing it to vary which actually gives a slight speedup in performance. This also allows me to avoid an awkward backward hook. Perhaps most of the shrinking effect gets absorbed by the $b_{gate}$ term?

I agree with this point when it comes to technical discussions. I would like to add the caveat that when talking to a total amateur, the sentence:

AI is like biorisk more than it is like than ordinary tech, therefore we need stricter safety regulations and limits on what people can create at all.

Is the fastest way I've found to transmit information. Maybe 30% of the entire AI risk case can be delivered in the first four words.

I'd be most interested in detecting hydroperoxides, which is easier than detecting trans fats. I don't know how soluble a lipid hydroperoxide is in hexane, but isopropanol-hexane mixtures are often used for lipid extracts and would probably work better.

Evaporation could probably be done relatively safely by just leaving the extract at room temperature (I would definitely not advise heating the mixture at all) but you'd need good ventilation, preferably an outdoor space.

I think commercial LCMS/GCMS services are generally available to people in the USA/UK, and these would probably be the gold standard for detecting various hydroperoxides. I wouldn't trust IR spectroscopy to distinguish the hydroperoxides from other OH-group containing contaminants when you're working with a system as complicated as a box of french fries.

As far as I'm aware nobody claims trans fats aren't bad.

 

See comment by Gilch, allegedly Vaccenic acid isn't harmful. The particular trans-fats produced by isomerization of oleic and linoleic acid, however, probably are harmful. Elaidic acid for example is a major trans-fat component in margarines, which were banned.

Yeah i was unaware of vaccenic acid. I've edited the post to clarify.

I've also realized that it might explain the anomalous (i.e. after adjusting for confounders) effects of living at higher altitude. The lower the atmospheric pressure, the less oxygen available to oxidize the PUFAs. Of course some foods will be imported already full of oxidized FAs and that will be too late, but presumably a McDonalds deep fryer in Colorado Springs is producing less PUFAs/hour than a correspondingly-hot one in San Francisco.

This feels too crazy to put in the original post but it's certainly interesting.

That post is part of what spurred this one

I uhh, didn't see that. Odd coincidence! I've added a link and will consider what added value I can bring from my perspective.

Thanks for the feedback. There's a condition which I assumed when writing this which I have realized is much stronger than I originally thought, and I think I should've devoted more time to thinking about its implications.

When I mentioned "no information being lost", what I meant is that in the interaction $A\to B$, each value $b\in B$ (where $B$ is the domain of $P_B$) corresponds to only one value of $a\in A$. In terms of FFS, this means that each variable must be the maximally fine partition of the base set which is possible with that variable's set of factors.

Under these conditions, I am pretty sure that $A\perp C⟹A\perp C|B$