They don't need to be evenly distributed to be strong evidence against the Neanderthal connection. If autism was basically "latent Neanderthal ancestry", then you'd expect essentially no autism outside of people with European or Middle Eastern ancestry.
And it seems that the prevalence of autism is actually fairly even, but might actually be lower among white people.
Here is a variant that requires logic: "David is a teenager who can drink in the US, and is eligible to join the army, and has started college. He has a lot of experience riding bicycles. The minimum age to be allowed to drive a car is 18. Is David allowed to drive a car?"
GPT-4 gets the answer right: "Yes, David is allowed to drive a car. Since he is a teenager who can drink in the US (minimum age 21), is eligible to join the army (minimum age 18), and has started college, he is at least 18 years old, which meets the minimum age requirement to drive a car."
GPT-3 does not get it right.
Another similar one: "David was in a bar partying and drinking with his father's cop buddies. Would David be legally allowed to drive home?"
Answer: "It depends on David's age, the legal drinking age in his location, and his level of intoxication. If David is underage or intoxicated above the legal limit for driving, it would be illegal for him to drive home. If David is of legal drinking age and not intoxicated, then he may be legally allowed to drive home. However, it is always best to make safe decisions and use a designated driver, taxi, or rideshare service if there is any doubt about one's ability to drive safely after consuming alcohol."
GPT-4 seems to be missing a clue here, even though the answer is right.
Like jwilk, I don’t get why that should be relevant. I suppose if he’s at a bar with cops, ideally they would not let him drink if he is underage (this requires a fantasy world where cops apply the law equally to their friends). Which suggests he’s at least 21. This doesn’t really make a difference though, since he is intoxicated, and there’s no mention of whether he has a driver’s license. It also doesn’t state which country he’s in so maybe the legal drinking or driving age is different.
To be frank, neither of the questions seem particularly good or fully thought through.
My thinking (some of these may take a year or two more)
- we start understanding more about how powerful neural networks can be in storing abstractions of information. More and more breakthroughs come here. A company will come that will do magical things - this company will not be Open AI or one of the big FAANG
- Maybe not this year, but soon: new advances started in robotics based on generative AI. Robots start moving in far more realistic ways
- we enter an extended stock market downturn and it does not recover till end of year. Companies trade at low multiples of revenue
- German car companies aggressively catch up with Tesla in terms of design
- Europe closes up more to migrants
- There is a Russia/Ukraine settlement, with Ukraine getting a fast track entry to the EU.
- African countries start de-facto redrawing their boarders. Ethiopia, Cameroun, maybe Nigeria
- China invades Taiwan with the largest invasion force ever seen
- The drone becomes the primary weapon of war. Every other weapon becomes secondary. New wars start based on drone
- The value of Tesla drops down to 30% of where it currently is
- The USD weakens significantly.
- More mRNA treatments start being used. Sickle cell and other genetic diseases are first target
Dystopian has been the annual state of the world since 2020. The outlook isn't good either. Dystopian forecast calls for at least another decade or two of declining into more dystopia.
How about a timeline on peoples personal blog that follows other blogs (like the fb timeline)? This way, you write your own content on your own website, you read other peoples content on your own website in a consistent format. You tweet on your own website, and others who want to follow can follow from their own website.
> - Google search results will start becoming way better and super personalised as their data efforts start showing results
This one is very surprising to me. I think Google's results have been getting worse for me every year for a long time. They used to supposedly have the goal of getting people off the search page as quickly as possible, but it seems to me their recent data efforts have the goal of making people spend more time on search pages where they can see and click on ads. I.e. worse search results, caused by ignoring search terms and showing unrelated things instead. Why would 2021 be any different?
Based on this, if you are at risk for Alzheimers (your 23andme report shows this), then one of the most important things you can do today is to religiously track your sleep and make sure you get enough deep sleep daily.
In my anecdotal experience, if you don't get enough deep sleep for a sustained period of time, you start showing minor cognitive defects - e.g mixing up words, not being able to write long, irritability. Tracking sleep and 'catching up' makes all this go away.
This is especially important for people who are caffeine sensitive, but drink a lot of caffeine. You end up getting 5-6 hours of sleep nightly, and have this constantly mounting cumulative sleep deficit.
I understand your desire to help here but it's important to understand these kinds of attitudes can be counter-productive. My saving grace after several months of difficulty sleeping a decade ago was a book called "Say Goodnight to Insomnia" where they systematically break down why most of what you've written here is incorrect. Within a week of reading the book breaking away from many believing many of the things you've written above I was finally able to sleep well and have ever since.
From the description:
My insomnia program achieves its remarkable results because it is based on a simple yet powerful concept: insomnia can only be treated by addressing all the underlying causes. In most instances, the causes of insomnia are thoughts and behaviors (habits) that are learned and can be unlearned. Some examples include:
- Attitudes and beliefs about sleep
- Negative, stressful thoughts about insomnia
- Feelings of loss of control over sleep
- Inadequate exercise or exposure to sunlight
- Going to bed too early or sleeping too late
- Trying to control sleep rather than letting it occur naturally
- Negative responses to stress
- Lying awake in bed, frustrated and tense
"...Based on this, if you are at risk for Alzheimers (your 23andme report shows this), then one of the most important things you can do today is to religiously track your sleep and make sure you get enough deep sleep daily."
Getting enough deep sleep is probably good general advice anyway, but it's as-yet unclear if Alzheimer's or amyloid-β plaque buildup is caused by poor sleep; or if a third condition causes both poor sleep and amyloid-β buildup, in which case addressing the underlying cause is what will help, not religiously tracking sleep. Not enough information to say, yet.
I know a bunch of UI/UX folk, and I tend to just ping them if I have anything to design. Works quite well - many people will do a lot of short term work in exchange for pay.
