The internet, online privacy and whatever else occupies my mind. I’m interested in a lot of things. The internet, technology and online privacy are themes that seem to stick for me. But there are also completely different topics that interest me. I also like to write, from time to time. https://dlay.eu/ Read more... You can reach me through email or find me on Mastodon. Entries
✍️Write rieview ✍️Rezension schreiben 🏷️Get Badge! 🏷️Abzeichen holen! ⚙️Edit entry ⚙️Eintrag bearbeiten 📰News 📰Neuigkeiten
I'm a student. And I'm very bothered to see how my fellow students are using LLMs. It worries me, as it's ruining the classes students spend hours on. I'll explain what I notice my fellow students do each day. This is a rant, but I hope it could also serve as a wake-up call to some fellow students, or maybe a teacher.
A concrete example that I witnessed just yesterday: the teacher asks us to fill in something called a 'core competence tree' for a business. Each student got assigned a different company, we got 15 minutes and then some students would be chosen to present the thing.
A core competence tree is a strange thing. If you didn't pay attention in class, you'd have a hard time making one. Some of my classmates also got assigned some unknown company. The person in front of me had to make an analysis of Cling Datacenters. You've guessed it: he fires up ChatGPT, types in 'make core competence tree of cling datacenters' and hits enter. This is the output when I try to reproduce it:
Creating a core competence tree for Cling Datacenters involves
identifying the key competencies that make the company
unique and successful. Here's a conceptual outline of what this
might look like:
### Core Competence Tree for Cling Datacenters
#### Roots (Core Business)
- **Data Center Operations**: Efficient and reliable management of data center facilities.
- **Customer Service**: Providing exceptional support and service to clients.
#### Trunk (Core Products)
- **Cloud Services**: Offering scalable and secure cloud solutions.
- **Colocation Services**: Providing space, power, and cooling for clients' IT equipment.
#### Branches (Core Competencies)
- **Energy Efficiency**: Implementing green technologies and practices to reduce energy consumption.
- **Security**: Ensuring the highest levels of physical and cyber security.
- **Scalability**: Ability to scale services according to client needs.
- **Innovation**: Continuously improving and innovating data center technologies.
#### Leaves (End Products)
- **Managed Services**: Comprehensive IT management and support.
- **Disaster Recovery**: Solutions for data backup and recovery.
- **Network Services**: High-speed and reliable network connectivity.
This tree structure helps visualize how the core business
and products support the competencies that lead to the end
products and services offered by Cling Datacenters.
If you need a more detailed or specific model, feel free
to let me know!
He typed the output in a nice graph and called it a day.
Now, I'm hoping I don't have to explain why this is a bad idea. Just for the sake of clarity, though, I will:
Get an assignment? Put the whole thing in ChatGPT. Need to write up a list of things to consider in terms of sustainability when making an investment? Open ChatGPT. Will something take more than 5 seconds of thinking? Chat. Didn't pay attention in class? Ask Chat.
All of my classmates assume whatever the LLM spits out is correct. Without an exception. Let me quote someone I worked with on a project recently: "ChatGPT said it so it must be right".
I honestly don't know anymore what LLMs are even good for. Getting inspiration, maybe? Asking questions that you then have to do research on yourself?
But: in no case can you expect ChatGPT to do the learning for you. It's not possible. Yet, that is literally what students do, all the time. The assignments which are supposed to make you learn a certain theory are outsourced to an LLM. The output is accepted and turned in without the student taking a second look. Result: the pupil turned in a worthless assignment, without ever thinking about the assignment himself.
Solution? Not sure. Probably involves educating the students about generative AI, showing practical examples of the tool failing at certain tasks. Helping them understand when it fails and why.
It'll be alright. There's no way for students to use ChatGPT on their exams. At least not on my university. The students know this, and thus practice for tests. I don't think a whole generation will go down. But if LLMs are allowed to be used for assignments in class, and students aren't made aware of the limits of these tools, classes have just become a whole lot less effective.
26.2.2025 00:00Students and their ChatGPTI came up with the following rule that I hold myself to:
If you come across a thing that you forgot you had, give / throw it away1.
Even if your reaction to finding the object again was 'OMG, how could I forget about this!! I want to keep it' - throw it away.
The fact that you've forgotten about it is a clear sign that you wouldn't have missed the object, had you never found it again. So, don't let the rediscovery of an item prevent you from letting it go.
Also, 'I paid for this' or 'I got it as a present' aren't valid reasons to keep the items. Don't let this kind of thinking be the sole reason of you keeping some object you don't want.
Decluttering feels good.
If the item could be useful to someone else, consider selling, gifting or donating it. ↩
You’ve probably been told that you need to use a VPN. You might have heard about encrypted DNS. What does all of this mean? I’ll try to explain how your device connects to a website, and the changes you can make to that process.
There’s a lot of false information out there. Some of it is simply outdated, but some is just marketing. Companies trying to scare you into buying their product. I’ll try to explain how these things actually work, without the BS. I hope I’ll be successful in laying it out clearly.
My goal: to help you make your own informed decisions about what measures you want to take to protect your internet activity. There is no solution that’s right for everyone. When trying to understand how this stuff works and making an informed decision based on who you want to protect your activity from, you’ve done some basic threat modeling.
Target audience: people who do not know how this stuff works yet, at all. All of this is an oversimplification. But I try to give you only the information you need to make the choice that's right for you.
Some definitions you’ll need to understand this post:
ISP: Internet Service Provider. The company that bills you by the month to provide you with internet, either mobile (3G, 4G, 5G) or for a fixed location (WiFi, ethernet).
DNS: Domain Name System. A.k.a. ‘the internet’s phone book’. To visit a website, you need to know its IP address. You don’t know its IP address, so you ask a DNS server what the IP address is of the site you’re trying to visit. All happens in the background.
If you changed no settings, this is most likely how you connect to a website.
You enter youtube.com in your browser. Your device asks the ISP-provided DNS for the IP address of youtube.com You then establish an encrypted connection to YouTube.
You enter youtube.com in your browser. Your device establishes an encrypted connection to your DNS server. It asks the server what the IP address of YouTube is, which it communicates to you through this same encrypted tunnel. You then connect to this IP address in the same way as above.
If it wasn’t already, now is when it gets complicated.
You connect, through an encrypted tunnel, to the VPN server. From thereon, your device acts if your VPN provider is your ISP: your device tells the VPN server you want to visit YouTube. The VPN server has an internal DNS resolver. It then establishes an encrypted connection to the YouTube server and forwards traffic from and to your device.
Now this is where we come to the actual threat modeling. If I succeeded in making an understandable explanation, which I sure hope I did, you now know what options you have and what this means for your privacy. Below, I'll lay out a few possible threat models.
The question you should answer here is: what data do you want to protect, and from whom?
If certain sites (like Anna's Archive or The Pirate Bay, for example)are blocked by the default DNS resolver of your ISP, using an encrypted DNS provider might resolve that.
Use a VPN.
Makes sense if you have a static IP address on a network you often connect from. IP address might then become a vector for sites (and advertisers) to track you. In this case, use a VPN.
However, if you're (mainly) behind CGNAT - meaning your IP address changes from time to time and is shared with others, you don't need a VPN.
Two options: Encrypted DNS will make it impossible for your ISP to keep a log of the domain names your device tries to resolve, but the ISP can still list the IP addresses you connect to. If only one website is hosted on this address, your ISP can deduce what site you visited. If there are multiple, there's no sure-fire way for the ISP to determine this. Using a VPN will prevent your ISP from knowing what you connect to altogether.
Look up information on data retention laws in your country. Where I live, ISPs are not required to log what sites you connected to. In many countries, they are. This should help you make the right decision for you.
So, what VPNs and encrypted DNS providers can I recommend?
Criteria:
1. I used the service myself and liked it
2. The service is transparent
This is obviously a very short and non-exhaustive list. You can find more options on PrivacyGuides. PrivacyGuides is an excellent resource that is community-driven and non-commercial. Relevant to this specific post:
An interpretive translation of De Krekels by M. Vasalis.
I lie awake in the darkness,
the curtains softly swaying,
my body weightless, formless,
my mind at peace, I listen....
Around me: the empty land with stones,
above: the empty sky with stars.
The beginning, thousands of years ago,
has never seemed so close.
Then, what I should not have heard:
the crickets' harsh, raspy voices,
millions of tiny, grating brakes
scratching the night.... it fades away.
And there is no rest. There is no night
endless and no silence still.
No great desire, no single will
can make it pause, even for a while,
the time that has already begun.
Despite the illusion of eternity
in quiet, still moments,
I hear a faint, sharp ticking,
I am haunted by the knowledge:
this too will slowly be worn away.
Finding interesting articles.
Sometimes, I like to read bigger publications like The Atlantic, The New Yorker or something from my own country. I also like to read articles from the so-called small web – sites like these. I find them using Marginalia, Kagi Small Web, and through other means. The small web are small websites run by people, not corporations. With the goal of sharing stuff, not generating profits.
Further reading: small web posts about the small web.
Saving said articles to Reeder (closed source, paid, indie).
Reading them, I barely do. There currently are 599 items in my reading list. Hmmm.
Pirating.
I download the movies and TV shows I want to see. I am subscribed to one streaming service, and I’m not going to subscribe to more. Immoral? Possibly. I do not care, frankly.
Freemediaheckyeah (open source) provides some great guides to get started. Things I like to use:
Anna's Archive for ebooks, and their initiative SciDB for accessing research papers (open source).
A site called 1337x.to for downloading TV shows.
A site called yts.mx for downloading movies.
Transmission for downloading torrents (open source).
Please note: this might not be legal in your country. It’s important to protect yourself when doing these things. A non-exhaustive list of ways to do so:
People like to use a VPN to protect themselves from ‘copyright trolls’ when downloading torrents. That works, but I personally use mobile data. I have an unlimited data plan. CGNAT (sharing IP addresses with hundreds of other customers of the provider) + the fact that in my country, the ISP is not required to keep logs on my activity, gives me enough peace of mind. This, though, is very specific to my situation and might not be a good idea for you. DYOR!
Use an ad blocker. These sites often contain malicious ads, which is why I didn't hyperlink two of them. Best case: Desktop. Safari (closed source) with Adguard (open source) or Wipr 2 (closed source, paid, indie), or Firefox (open source) with Ublock Origin (open source).
Visit my favorite news site mindlessly throughout the day.
I really should stop doing this.
Starting up random projects, that I abandon soon after.
I don’t plan to do that with this blog, however. I’ll publish when I feel like it and just leave it be when I don’t.
I've had this discussion with someone very close to me recently. We didn't come to an agreement and I'm certainly not done thinking about this topic. I will lay out both of our arguments here.
My opinion
For all societies, throughout all of human history – life has always been unfair. Life has always been hard. However, despite all this misery, I believe humans are hard-wired for happiness. I think that of all people ever, a great majority viewed their lives as worthwhile.
No matter if you unjustly get put in jail, are a farmer in a feudalist society in medieval times, a slave in the Roman Empire, or something entirely else. I believe chances are big you would consider your life worthwhile when asked – all things considered. Life, for most people, is full of beautiful moments that, however small, make up for the bad.
I'm not a psychologist, biologist or expert in any other way so my opinion on this subject is not scientific. This is just the way I feel the world works.
Their opinion
We are lucky, living in a free and prosperous society. For most people, life has not been 'worth it'. The misery caused by all the oppression, wars, health crises (or lack of healthcare), inequality, child deaths and so on made it that way. This has always been the case, unfortunately.
Happy lives are something only found in privileged circles, the lucky few in a skewed world.
Abstraction
My opinion goes with the assumption that happiness is largely unrelated to circumstances, that it's an experience somehow part of nature rather than nurture. The person I had this discussion with believes the opposite. I do not know who is right. Am I naive and are they realistic, or are 'in-touch' and 'cynical' more accurate terms to describe our convictions?
I intend to find some credible research to back either of our claims.
20.2.2025 00:00Hard-wired for happiness?