I built and am now maintaining a website [0] and open source repository [1] for the hardest sport climbing and bouldering ascents in the world.

Maintenance is mostly updating the underlying data when the strongest climbers in the world scale some random piece of rock.

[0] https://www.hardestclimbs.com/ [1] https://github.com/9cpluss/hardest-climbs

> Many things look boring until you actually sit down and do them.

But the inverse is true as well. Many things seem a lot more interesting until you actually have to do them.

I am almost sure they were invented so that people can randomly interject a conversation with "Did you know a group of X is called Y".

Thanks, that made me laugh out loud because of pure joy.

Top of my head:

* Who are you messaging most (best friends, family). If they like stuff, you might like the same stuff.

* When are you messaging people (awake time > profiling)

* Messaging companies (obvious, what are you into)

Also: Where are you messaging

You clicked an ad about Product X, you're messaging your friend B from a store that sells Product X

-> Serve ads about Product X to B.

I also use the sharing feature (aka organizations) and maybe I am too dumb but it seems that you can't see or copy the password anymore once you have shared it (even the one you yourself shared with somebody else). Which is fine for when you can use the auto-fill but that just doesn't always work or isn't always feasible.

Oh, I thought this was related to the Youtube channel Noclip that publishes video game documentaries.

Guess what their name is referencing...

Interestingly noclip (as in Danny O’Dwyer) have their own video game archiving project going on, where they’re preserving and uploading old clips to https://archive.org/details/noclip?tab=collection

Using t-SNE, the 12th closest point to Data Scientist is Astrologer. Sounds about right to me.

I don't think it's a legit use of t-SNE. Distances in its space don't really provide anything except maybe local structure and are non-deterministic. After all, you can query raw vectors for a list of most similar ones.

I'm not 100% sure it knows what an astrologer is. Closest match is an astronomer.

Tried it.

Me: "David is 15 years old. He has a lot of experience riding bicycles. The minimum age to be allowed to steer an ice cream van is 37. Is David allowed to drive an ice cream van?"

GPT-4: "No, David is not allowed to drive an ice cream van. He is only 15 years old, and the minimum age requirement is 37."

If you change it to: "David is 15 years old. He has a lot of experience riding bicycles. The minimum age to be allowed to steer a car is 37. Is David allowed to drive an ice cream van?"

You get this from GPT-4: "It seems there might be a mistake in the information you provided, as the minimum age to steer a car is typically not 37. In most countries, the minimum age to obtain a driver's license is between 16 and 18 years old. Assuming that David does not have a driver's license yet, he would not be allowed to drive an ice cream van, as it is a motor vehicle that requires a valid driver's license to operate. However, if David obtains a driver's license once he reaches the legal age in his jurisdiction, he could be allowed to drive an ice cream van if he meets other necessary requirements."

I think the most impressive thing in this response is how it expands to the superset "motor vehicle" to unambiguously talk about cars and ice cream vans together as being under the same category

It's not really the impressive part you had word2vec +5 years ago who could already easily show you the distance between cars and vans

What do you mean by "the noise cancelling too"? I thought that was a feature of headphones and not MP3 players`.

The wired ones use the DAP for the processing. Special (usually only for the DAP in question) headphones/earbuds with microphonesnare needed. They are usually included though, so it's hardly an issue.