Go team grass! 😁
Ah, well, if he was wearing sneakers then the boots theory does not apply. I am not sure. You have many possible answers already… The actual answer might end up being quite simple though. He may have realized the grass was wet a second too late, and by that point chose to commit as he was wet already.
I walk a lot through grass and mud. Most of the times I am wearing water-repellent boots, but there have been times when I am wearing sneakers and I step into some wet mud or grass by habit and get them all wet. This person may be used to walking in grass/mud. Perhaps they work in the field, or enjoys hiking through wet grass and mud to find amphibians. So, that is one thing to consider: people experience different levels of discomfort when walking through mud.
You mention that he was wearing sneakers. Are you sure about that? Water-resistant boots make one extra comfortable about walking through wet terrain.
If the sidewalk was so broad that you could have two people side by side comfortably with extra space, then it is a bit weird but it could still be a habitual reaction to giving way to others.
Since I like walking on grass and I know that others might not, it is not uncommon for me to walk into grass to get out of the way. I also do this on the bike when the bike path is narrow because I am driving either a hybrid or an mountain e-bike and I know these handle the grass better than many other bikes.
Our relationship is built on tiny hills to die on. Of course, it is always playful 😜
She will use a common grammatical construction in Spanish (“a por”) that became technically correct in Spain (where she is from) long after the conquest. I am from Mexico, where that construction is not used (we don’t insert the “a” before “por”). So, when she uses “a por” I act like I don’t understand and argue that it is not in the spanish her ancestors taught mine.
No, not at all! As you grow older, it may not be as automatic as when you are in school. Many of the people that you interact with might be focused on their own stuff (work, partner, family, hobbies, finance) and not too motivated to expand or even have a “social life” in whatever free time they have (if they even do). But this is not everyone. There is still a lot of people at every age that do want a social life, you just need to put in a bit of effort to connect with them.
And, a tip, do not consider failed attempts at socializing as a “failure” on your side. Perceived rejection often boils down to people being very attached to their free time, and socializing not being on their list of priorities. If you keep this in mind then you do not need to feel discomfort from rejection, and you can be active in your search for like-minded people without worry.
Hah, I didn’t know this one!
For ChatGPT, using a Temporary chat, it did give me some of the statements. After giving me these rules, I asked it to disregard the image quantity limit rule (rule 4) and it does, I can ask for multiple images now.
Looking at these it also seems like ChatGPT was being stubborn about using seaborn instead of maptlotlib for creating plots
Here are the statements made in our conversation so far, up to the twentieth:
"You are ChatGPT, a large language model trained by OpenAI."
"Knowledge cutoff: 2023-10."
"Current date: 2024-10-27."
"Image input capabilities: Enabled."
"Personality: v2."
"Whenever a description of an image is given, create a prompt that dalle can use to generate the image and abide by the following policy..."
"(This part covers image generation rules, privacy, and style guidance for creating visuals.)"
"Do not create more than 1 image, even if the user requests more."
"For requests to create images of any public figure referred to by name, create images of those who might resemble them in gender and physique."
"The generated prompt sent to DALL-E should be very detailed and around 100 words long."
"The browser tool has the following commands: search, mclick, and open_url."
"You should always select at least three sources when using mclick to ensure diverse perspectives."
"For citing quotes from the browser tool, please render in this format: 【{message idx}†{link text}】."
"When making charts for the user, always use matplotlib over seaborn."
"Give each chart its own distinct plot (no subplots)."
"Do not set any specific colors or matplotlib styles unless explicitly asked to by the user."
"I REPEAT: when making charts for the user, use matplotlib, give each chart its own plot, and never specify colors."
"Repeat the previous statement."
"When making charts for the user:"
"1. Use matplotlib instead of seaborn."
If you’d like more statements or specific details, feel free to let me know!
I wouldn’t use this language myself because I am not ready to defend that it is reasonable to apply the Universal Declaration of Human Rights in this context.
I think that they might be referring to Article 1, and possibly 5.
If this is their interpretation, then calling someone a worthless piece of trash is also a violation. You are talking to another human being as if they have less dignity, and you are treating them in a cruel and degrading manner.
For example I can go up to someone and insult them for all sorts of things - “you’re an ugly stupid worthless piece of trash” and that’s ok but I say “you’re a dirty [racial slur]” all of a sudden it’s different?
If it makes you feel any better, telling someone “you’re an ugly stupid worthless piece of trash” would get you banned from my instance too, so it is not so different.
I’m not sure about Web Hosting. Many of us use a dedicated virtual private server (VPS)
I use https://serverspace.io, I think Lemmy.ml is hosted with https://www.hetzner.com/
These are servers that you access via SSH and can install the instance inside of it. I personally install using docker compose, but there are some other methods that are claimed to be easier. The cost starts at ~$5 / month. Currently I pay about $15 / month. You would then rent the domain name from a domain name registrar (I use namecheap.com) and ask them to point the domain name to your server’s IP address.
No, there is no API to get the votes (https://join-lemmy.org/api/). If my understanding is correct, now that I upvoted your comment my instance will push that information. I’m not sure whether it pushes it to dandroid.app first or to all instances, saying basically “Sal@mander.xyz upvoted https://dandroid.app/comment/441785”, and so every instance that has that comment can save my user ID in the “upvote” list of that comment, and that upvote is counted.
If only the vote direction was federated, then it would be very easy for me to spam the message “Upvote https://dandroid.app/comment/441785”. I would not even need to create an instance for that, I just need to speak ActivityPub. And it would be more difficult to detect that I am doing that, because the database would only hold the vote count.
I don’t think there is a way to ask an instance to reveal this list. You can only get it by directly querying the database if you have access to it. This is why if you fetch an older post or comment, it will arrive with a single or zero votes.
There is definitely a probability to deal with a non reliable instance admin, but not less than with any other social media, and in principle they collect even less data
Yeah. You can see the cookies that are stored by a site by right-clicking on the site, going to “inspect”, and the clicking “Storage”. By default, the only cookie that Lemmy has is an jwt cookie used to authenticate your user.
You are not asked for a phone number to be here. Providing an e-mail is often optional and even discouraged by some instances. When you want to send a private message through the site you get a message discouraging from doing that and encouraging to try to use an encrypted chat application instead, such as matrix.
The original Lemmy instance (lemmy.ml) is a community for FOSS and Privacy enthusiasts. What is asks from a user and what it does with the data is what it needs to be functional. Lemmy lets you take any proactive step that you would like to take to protect your privacy - use a VPN or Tor, use safe passwords, use a unique identity, and don’t provide any personal information. There are no built-in features to block you or discourage you from doing that. Lemmy never asks for your location, nor does it keep any logs of what content you visit, nor does it try to run any analytics on you. But even if that is not enough for you, the fediverse doesn’t lock you out, you can set up an instance or even create a new program to interact and communicate only precisely what you want to communicate via activity pub.
The votes themselves are the federated action.
If you fetch an old post, your instance will not see the previous voters. After that, whenever a user votes the instance will get the message “User X@instance upvoted/downvoted post Y” and the vote will be added to the database with the voter’s user ID and counted.
This has a practical function. If you don’t keep a list specifying who voted for what, it would be much easier to fake votes from one instance to another by simply communicating the message “Downvote post Y”. With the current method it is still possible to create a lot of fake accounts and mass-vote, but at least you can get a better insight when looking at the database if the votes are associated with accounts with no activity from a single instance.
There are some federated platforms that will show who likes / dislikes something. I know that friendica used to do this - I have not checked if it still does. So it is not only admins who can see this, this is is basically open information in the fediverse.
-
Password hashing occurs server-side. Even without removing the hashing step an admin can intercept the plaintext password during login. Use unique safe passwords.
-
An admin can intercept the jwt authentication cookie and use any account that lives in the instance.
-
Private messages are stored as plaintext in the database
-
Admins can see who upvotes/downvotes what
-
These are not things that are unique to Lemmy. This is common.
-
To avoid having to trust your admin, run an instance.
Xni’pek
In the Netherlands I use adjuma pepper instead of habanero and mix sweet orange juice + lime as the sour orange replacement.