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.
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.
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.
I only recently started working in a big team again and when I'm doing Github code reviews I often find myself checking out the branch locally and reading the file in my IDE and then going back to the Github interface to write my review comments.
Not only is this often the only way to understand the context of a change but it also makes it much easier to spot refactoring opportunities. But it's cumbersome and slow.
What I found most irritating was that even reformatting the drive (in any file system and on different machines), would not make the drive work again. After plugging it into my Mac the FS would corrupt again.
You're quoting from a section of the text where they are explicit in their responsibility to disprove that they use distancing language in a different section of the text.
> Even something as simple as only showing you tweets from people you follow (what a concept!) would revolutionize the experience and drastically reduce the need for moderation.
You can do that right now by turning off retweets for the people you follow. You have to do that individually for every user you follow but it allows for a highly curated timeline. I turn of retweets for about 80% of the people I follow because I am interested in their original content but not in their random retweets. The other 20% introduce me to new content through their retweets.
> It's worth noting that there was an apparent real opportunity to resolve the Russia-Ukraine conflict in April 2022, via diplomatic negotiations, but UK's Boris Johnson reportedly disrupted those talks by threatening to withdraw UK/US support for Zelensky if he proceeded with negotiations.
Do you have a source for this claim? I heard this argument before from an acquaintance and it completely contradicts my reading of the situation in April.
Including, apparently, the people who created the web site, and who use bold text and different font sizes to format the headlines, colors to indicate features which are supported and not supported, and an image of a "plaintext certified" stamp.