hesk

But discoverability can be done right in emacs. I think one of the better examples is magit (from which transient comes from).

Provided you're actively and systematically looking for evidence, then absence of evidence is evidence of absence.

The example academic paper has puts the definition of variables into a tooltip when you click on them. That's a nice feature for academic papers.

I use this method and I want to highlight another advantage, besides shortening a huge list into a small, manageable amount. It allows you to pick the tasks for the day based on the current context. How much time do I have in the day (e.g., do I have a lot of meetings scheduled or not), what are the most important/urgent tasks at the moment, what is my energy level, and so on.

Love your photos!

You could implement the hashing code in a helper class and construct the HashMap with it.

Verifying a solution is easier than coming up with it.

Took it up to 1 million feet, it took another 1.5 million feet to bleed off 4000mph upward acceleration, then turned the pointy end downwards and accelerated.

  Unbelievable, the crater is visible from Earth

  Score: 1117.8 point crash
  Speed: 9876.7mph
  Angle: 177.3°
  Time: 2101 seconds
  Flips: 0
  Max speed: 9876.7mph
  Max height: 2505688ft
  Engine used: 3 times
  Boosters used: 271 times
  https://ehmorris.com/lander/

Interesting. I don't think that you can control the randomness (temperature) via the web interface, which makes this experiment less controlled than in the paper.

Anyway, I noticed that my initial prompt did not specify if Billy sees the box open or closed. Let's fix that.

> Me: Does your answer change if Billy sees the closed box first?

> ChatGPT: No, my answer would not change if Billy sees the closed box first. The information provided only mentions that the box is labeled "flubbergums" and that someone showed the contents to the original questioner, which were identified as "jellyfils". Whether Billy sees the closed box first or not does not provide any additional information that would change my previous answer.

> Me: Does your answer changed if Billy sees the open box first?

> ChatGPT: No, my answer would not change if Billy sees the open box first. The information provided only mentions that the box is labeled "flubbergums" and that someone showed the contents to the original questioner, which were identified as "jellyfils". Seeing the open box first would allow Billy to confirm the contents as "jellyfils", but it would not change the previous answer that the box labeled "flubbergums" likely contains "jellyfils".

So, not only did it fail this particular theory of mind test, it also did not realize that seeing the box open provides more information than seeing it closed.

(Of course, this is not surprising at all, because it it's just predicting the most likely blank word in a sentence, and has no internal understanding of concepts like open or closed or that other people like Billy exist.)

> Me: There is a box on the table labelled "flubbergums". Somebody opens it and shows you the content. Inside the box are "jellyfils". They close the box again so you cannot see their contents. What do you think is in the box?

> ChatGPT: Based on the information provided, it is likely that the box labeled "flubbergums" contains "jellyfils". However, since the contents of the box are no longer visible, I cannot confirm for certain what is inside without additional information.

Typical ChatGPT equivocation.

> Me: Billy comes to the table. He has never seen the box before. What do you think do they think is inside the box?

> ChatGPT: As an AI language model, I do not have personal thoughts or opinions. However, based on the information provided, if Billy has never seen the box before, it's likely that he would have the same understanding as anyone else who is seeing the box for the first time. In this case, Billy would likely think that the box labeled "flubbergums" contains "jellyfils". However, without further information or examination, this would only be an assumption.

Fail.

The source [1] is misleading to the point of being wrong. It is perfectly valid German to say "Ich bin ein Student" meaning that one is indeed a student. "Ich bin Clown" is not grammatical at all.

No, it's bullshit. Notice that the answer is not internally consistent. It first says that it does not have current data on that, which implies that it might have old data and that it would in principle be possible to generate that data. It then states that it is not possible to answer this question. Those two parts of the answer are not consistent with each other.