PhD student at the University of Toronto, studying machine learning and working on AI safety problems.
https://www.microcovid.org/paper/2-riskiness#fn6 discusses https://covid.joinzoe.com/post/covid-long-term which has an app-based survey claiming 1 in 10 people still have symptoms after 3 weeks. (but since people can just sign up for the app I'd guess this is harder to know how to interpret than the telephone survey). Microcovid.org uses this 1 in 10 figure as the estimate for chance of some ongoing health consequence, and claims the risk of ongoing health problems from a 1% chance of COVID is equivalent to the risk from 1 year of driving (but this comparison involves even more assumptions).
https://www.cdc.gov/mmwr/volumes/69/wr/mm6930e1.htm found that ~1 in 5 of 18-34 year olds with no underlying health conditions had symptoms 3 weeks later (telephone survey of people who'd been symptomatic and had a positive test).
Other discussion in comments of https://www.lesswrong.com/posts/ahYxBHLmG7TiGDqxG/do-we-have-updated-data-about-the-risk-of-permanent-chronic
Not addressing fatigue, and just a study in progress, but this study is looking for long term neurological problems, might another weak bit of evidence when it releases results https://www.cambridgebrainsciences.com/studies/covid-brain-study
Seems like it could be helpful if people who've thought about this would also predict on the question of what the survey value would be today. (e.g. via elicit snapshots)
Google's Meena (2.6 billion parameters, February 2020) creates original puns in "Conversation D", and I think "Cross-turn Repetition Example 2" is absurdist comedy, but maybe more as a result of the way the model fails.
Human: I like how cute cows are
Meena: Ah, interesting. You like how they are cute, right?
Human: yeah, and they’re realy smart
Meena: I heard they go to college
Human: cows go to college?
Meena: I heard that a cow went to Harvard.
Human: what did the cow study?
Meena: Bovine sciences.
Human: do horses go to Harvard?
Meena: Horses go to Hayvard.
Human: that’s a pretty good joke, I feel like you led me into it
Meena: You were trying to steer it elsewhere, I can see it.
Are there any sources that describe why 14 months is the trial period (or provide justification for picking trial periods of various lengths)?
Seems like it ought to be more of a continuous variable, rather than this discrete 14 month trial: at time t, we've observed x people for y months to see if they have wierd long-term side effects, so we should be willing to vaccinate z more people.
The chrome extention Netflix Party lets you synchronize playing the same video on netflix other people, which you can use along with Skype to watch something together.
(You can always fall back to counting down "3,2,1" to start playing the video at the same time, but the experience is nicer if you ever need to pause and resume)
The worry I'd have about this interpretability direction is that we become very good at telling stories about what 95% of the weights in neural networks do, but the remaning 5% hides some important stuff, which could end up including things like mesa-optimizers or deception. Do you have thoughts on that?
Might be interesting to look at information that was available at the start of H1N1 and how accurate it turned out to be in retrospect (though there's no guarantee that we'd make errors in the same direction this time around).