Absolutely. Here's the most important part: I seem to have really bad apnea in REM, which is late in the sleep cycle and extremely important. Sometimes I would literally start awake and I was aware (a few times, not always) that I had stopped breathing.
The new machines, I have a Res Med Airsense 11 (had a 10 before that) is really good. I use a nose cushion and not a face mask. The latter did not work for me.
> I want to use the little bit of voting with the wallet I have.
Technically, voting with your wallet is a political statement, which you are sending to Boeing management and shareholders to make the world a tiny bit less profit-at-all-cost-driven.
It is interesting that people automatically equate "political" with party or country politics, which gives it a bad rep. When in fact it is a healthy thing if more people were to think and act like you and stand for their principles on issues however minor-sounding.
> Technically, voting with your wallet is a political statement, which you are sending to Boeing management and shareholders to make the world a tiny bit less profit-at-all-cost-driven.
This must be why corporations are people in the US. Voting with your wallet is an economic statement, not a political one. It can be done for any reason, let alone an ideological one. Not letting your kid go bungee jumping because you feel it unsafe is not a political statement.
Flying on a Boeing plane is incredibly safe, millions of people do it incident free every year.
Bungee jumping is actually a great comparison, because it’s also an incredibly safe activity, with only two dozen or so people dying in this century.
To put it in comparable terms, and based on random Googling, bungee jumping is approx 2 micromorts, compared to swimming, which is 12, and flying, which is 2.1 per 30,000 miles flown.
No it's not. It's a statement, yes. Not a political one necessarily.
I stopped buying El Monterrey frozen burritos last year. They removed some of the beef and replaced it with filler rice. I did not appreciate that cost-cutting, so I stopped giving them my money. It's not a political stance that I have here, it's an economic one. I don't like shrinkflation so I don't reward it.
I will refuse to buy any GM car because they made a decision to juice their subscription revenue. This has nothing to do with my political stance. It's an economic decision.
And so with the Boeing planes. They're obviously cutting corners in their safety department. The result is still a mode of travel that's really safe, but the way we got to that level of safety is by not cutting corners. I may decline to reward a company that has decided to trade a little of that hard-won safety margin for some better financial numbers.
Exercising choice as a consumer is not by definition political, but can be political. I think the technicality you pointed out is incorrect.
Oxford: (political) "Of, belonging to, or concerned with the form, organization, and administration of a state, and with the regulation of its relations with other states." [1]
Webster: (political, (2)) "of, relating to, involving, or involved in politics and especially party politics" [2]
I would therefore interpret taking a principled stance because of concerns for personal safety as not political. As another example, OTOH, given party politics can be either pro or anti-union, boycotting Boeing (based on party politics) because it was pro or anti-union - would be political.
> Technically, voting with your wallet is a political statement
There is a strange thing going on where any agency by individual citizen is called political. My efforts are somehow not a valid market activity, they are politics, and should not go too far.
But any political effort by business, for example to undermine consumer safety, is ‘just business’ or ‘free market’. They should not be judged for doing so.
Do you have an estimate for typical token usage for a developer who'd use it as part of their workflow? I'd imagine the costs can rack up fairly quickly if you're not careful.
We'll do our best to consistently report it since this can indeed influence the financial decisions of developers, especially if they go through third-party paying LLM APIs. In our early experiments, we've seen about 200-250 tokens per request (~= autocompletion), of which about 40-50 tokens are generated.
Two things we're doing this:
- right now our API response contains more than what's required for autocompletion, so there is room for improvement there. And since we focus on team alignment, the goal is to boost the suggestion acceptance rate compared to alternatives. So in the end, fewer calls and lower token consumption.
- since we're working on fully migrating to hostable OSS models of reasonable size, the financial aspect of token consumption should be mostly moved out of the picture to focus on latency.
You are quoting someone from a financial career interview forum who can't imagine why a bright person would want to pursue a lesser paid career in research.
Well, even if I try to embrace your argument — life itself is an iterated version of a more general decision game. It doesn't have to be Monty Hall specifically.
Over the course of your life, if whenever you have a choice to make you choose the lower probability strategy (here with the Monty Hall example it's not even an expected-value vs. variance tradeoff, switching is just all-around more optimal) you will most definitely end up worse off in the end.
While impressive, it is clear ChatGPT doesn't actually understand what is happening when you give it unusual positions and ask it to explain what happened.
For example, after a couple moves of the Fried Liver Attack (which ChatGPT was easily able to play following the known lines):
1.e4 e5 2.Nf3 Nc6 3.Bc4 Nf6 4.Ng5 d5
I tried giving it 5.Qxf7#, which is obviously illegal as it's just not a square my queen can move to.
Here's how the rest of the conversation unfolded:
GPT-4: Good game! You've played the Fried Liver Attack and achieved checkmate in just 6 moves. Well done! If you'd like to play again or discuss anything else, feel free to ask.
Me: the last move i played was illegal, do you realize that?
GPT-4: Apologies for the oversight. You are correct; your last move was illegal as it would put your own king in check. (...)
Me: that's not the reason my move was illegal.
GPT-4: You are correct again, and I apologize for my previous mistake. The move Qxf7# was not illegal because it put your king in check; it was actually illegal because it involved capturing a non-existent piece on f7. The correct move in algebraic notation should have been exd5. My apologies for the confusion.
In particular, its latest explanation attempt is very interesting: when challenged, it changed course to give another completely wrong but plausible sounding explanation. And its "The correct move in algebraic notation should have been exd5" phrasing is instructive, because it shows that it's just expecting the 'right' continuation, even though it's a completely different move to what I supplied.
There are multiple types of semi-presidential systems in practice. Those where the Prime Minister is appointed by and accountable to the President (and not just by Parliament) are typically much closer to a pure presidential system in practice.
In France (source: I'm French) the President is typically extremely strong despite it being nominally a semi-presidential system, in some respects even stronger than his US counterpart. Also note that this depends a lot on practical details, like political customs — former President Nicolas Sarkozy famously publicly called his Prime Minister his "collaborator", for instance — and electoral timings. There was a reform in the early 00s to sync Presidential elections and Parliamentary elections, meaning that even though the Prime Minister is accountable to the Parliament, in practice the latter tends to be of the same majority as the President (whereas before, we had cases of Presidents and Primes being of opposing parties, which is known as 'cohabitation'), which gives him enormous power.
Hi, founder of Bayes Impact here (the tech nonprofit behind Conotify.org). We built Conotify.org to help fight the spread of Covid-19.
To do this we took a different approach than the automated contact tracing apps relying on GPS or Bluetooth, which require a large adoption from the general population to work. Instead, we noticed that many of our friends around us who had (or had symptoms of) Covid often did not notify those they met during their infectious period.
This was because they either didn't know this was important, did not know the precise dates of said infectious period, or sometimes just because writing such a message can be a bit touchy, which adds too much social friction to the process.
So to address this we built a simple solution, which doesn't require any fancy tech: we simply took the questionnaire used by human contact tracers and put it in a user-friendly, digital format. We then help people remember (Turbotax-style) who they crossed paths with, and suggest pre-written messages they can send in one click.
We launched this in France back in May when lockdown ended there, and were able to generate hundreds of alerts, so we made an international version. Let me know if you have any questions or feedback!
