AI: Excitement!

Old 8086 according to the AI!It feels like we have started over. The first few years where home PC’s got popular were weird. Things were clunky, and very fluid. Some games and programs required a bit more memory, of a bit of a better graphics card, and I would take out and update my graphics card, or get some extra memory, and open the PC and put the memory in the slots available on the motherboard. It was just how it was. CD’s got popular? Simply get a CD reader and plug it in. Zip-disks got popular? Get a SCSI extension for your PC, plug it in on your motherboard, connect your new zip-disk to the new SCSI port and hope for the best. A hard-disk? Get the really expensive 20MB HD and plug it in. Format and partition the HD and after a couple of hours everything was ready to go. USB connections? Get an extension, plug it in, and you are ready to use whatever you got.

After some years things got less fluid. PC’s came all equipped, and updating was not so usual anymore. Games could basically always run, although sometimes a bit slower, depending the hardware you had. All systems had a hard-disk, and USB connections. Things got easier with every new generation of hardware.

I know the AI (more accurate, the LLM) we now have is not hardware, but even being software it feels like old times. Trying models, and different setups. Making choices, because some models are just to big, and don’t fit on your drive. Waiting and trying to improve the setup, adding speech or image or music generation, try what works and what doesn’t. If kind of fun again. Reading and investigating, and slowly getting results.

When my laptop gave an answer to my first question, without having to connect to the Internet to do a search it felt exactly the same as when I added a strip of 4 MB of memory, and it worked, and I could run some new program. Exciting, another leap into the future!

Bot or not?

Monkey!The last comment on this blog is from September last year. A certain Ricky posted a comment on my tide clock post. The strange thing is that the comment is on topic, but still misses the point. The last sentence is that the person would like to see the result. But ‘the result’ is exactly what the post was about.

What a creative and fun project! A tide clock is not only practical for beach lovers like you but also a unique piece of decor. It’s great that you’re taking the DIY approach to create something that perfectly suits your taste. The step-by-step process you’ve outlined seems both simple and rewarding. I can imagine it will be really satisfying to see the tides reflected on your custom-made clock! Looking forward to seeing how it turns out.

It looks like this comment is generated by some kind of AI, where this kind of comment has only one goal. To get on the list of accepted comments, so that in the future comments from this user are automatically approved. Once that is achieved, there will be a tsunami of messages about gambling, sex, crypto, and medicines arriving on every page.

Pump & Dump

Pump and Dump!Step 1: Acquire an asset for yourself.
Step 2: Make the asset attractive to others.
Step 3: Wait for others to buy in, and the value goes up.
Step 4: Sell your holdings.
Step 5: Profit for you, losses for others.

It is unethical and illegal to make money through Pump and Dump schemes, but this does not stop the rich and famous from doing it. The world’s richest man has done it at least twice. He mentioned that ‘Dogecoins’ were a great investment, then sold his holdings a couple of weeks later. He also announced that Tesla would accept Bitcoin for car payments, causing the value to surge. He then sold his own coins and canceled the acceptance of crypto for payments. A lot of profit was gained by Musk, while the losses were borne by others.

Tips for Identifying Schemes:
– Be cautious of sudden, unexplained price increases. (Like now)
– Verify information from multiple reliable sources.
– Avoid investments that seem too good to be true. (Like now)

Musk seems to favor the ‘Pump and Dump’ approach because, with a large enough following, it is easy money. A lot of money. His now friend Trump has one defining characteristic: for Trump, money is the most important thing. Money is the only thing that matters. Together, they could be preparing the biggest pump and dump the world has ever seen. The richest person in the world, with the most powerful person. Together, they are now pumping crypto a lot. The value is going up like a SpaceX rocket. The question now is simple: when is the dump coming, and how much damage will it do?

Insufficient funds

Money gone!Friday, after work I pass by the supermarket near my office. I go to this supermarket a lot, so I work my standard route and get everything we need. I stand in line to pay and take everything home. That was the idea, buy paying was not so easy. Payment declined. Insufficient funds. Another card did work, so I loaded everything into the car. After loading everything I decided to check the bank app to see why I could not pay, and I got quite a scare. There was nothing left on our account. Everything was spend in Marceille, in France. Our entire account, with nearly 1500 euro was all spend in a single day.

We quickly went through all the steps. Notify the bank, block all cards, change all codes and passwords. Make a declaration and file a report at the police station, and now all we can do it hope we will see some of our money back.

The thieves did make an error. They made a purchase that makes them identifiable. Using 100 of our euros the thief booked a hotel room in booking. Maybe he felt like going on a city trip and just enjoy life a bit. The weird thing is that booking knows all their data. The thief connected my bank card with his booking account to rent a hotel on his/her name. This should make it easy to find the thief. Still, I am afraid nobody will make the effort to find the perpetrator. Booking will never reveal any identifiable data to me, the police will probably do nothing, and just file our report, and the bank will probably make a calculation. Doing an expensive investigation for 1500 euros, with a low probability of doing anything with the thief, and a very low probability for getting the money back is not going to be justifiable expense. To bad, but it seems the thief will get to keep their stuff, paid with our money, and will not face justice any time soon.

Online friends / Astroturfing

a big ear with lots of people whispering in itMore and more time is spend online. Your social circles are formed online with people that feel similar to yourself. Where our social circles used to be centered around the town or city where you live, right now they can be everywhere. The same way that your physical friends can influence you, you can now also be influenced by the options and views of your online friends. Friends that you might have never met, but with whom you can spend lots of time.

Imagine a very near future where your online friends might all think siilar to you. A bit group of similarly minded people. All individuals that reinforce your thinking in a certain manner. Maybe 10 good friends, and maybe 20 more people who also think in a similar way. Maybe such a big group of people can influence you much more that you would think possible. Each of the persons you know has his or her own personality, which you get to know and trust.

Imagine all these friends are not as you would think. All of them are uniquely generated by an AI. In the blink of an eye there can be tens or hundreds of people who all think the same as you, and who will all try and navigate your thoughts to a desired outcome.

Maybe suddenly some of them will tell you about their experience with a new product, using the AI’s for some kind of advertisement. Or worse, your ‘friends’ influence your political opinion. This has already happened, where less powerful AI was used to influence groups of people and to redirect their thoughts and actions to achieve a certain goal. Now, with AI getting more and more accessible, the big danger is an abuse so personal it will be very hard to resist. You will not even know it is taking place.

If can even be done with less effort. Simply train an AI on how you interact with your environment. Let it learn how your friends and contacts behave, and at the right moment simply inject some additional conversation. Almost impossible to trace.

Even if this technology is used for good, avoid radical opinions, avoid unwanted behaviour, in the end the person that controls the AI controls the emotions and thoughts of lots and lots of people. A very dangerous future we are entering.

Lets just ask an AI itself

Would it be possible for an AI to generate a number of different identities all aimed at trying to influence someone to get them to buy a certain product?
Yes, it is possible for an AI to generate multiple identities to influence someone to buy a certain product. This is known as astroturfing, which involves creating fake identities or groups to simulate grassroots support for a particular cause or product.

The number of identities needed would depend on various factors such as the size of the target audience, the level of influence required, and the resources available for the astroturfing campaign. It’s difficult to provide a specific number without knowing more details about the specific situation.

However, it’s worth noting that astroturfing is generally considered unethical and can damage the reputation of both the product and the company behind it. Therefore, it’s important to approach marketing and advertising ethically and t

AI: Are we there yet?

A mind inside a fishbowl on top of a mechanical body walking through the sky on top of a cloudArtificial intelligence is a thing we keep hearing more and more about, but what are we really talking about? Is it really something smart and intelligent. It is certainly smart, but sadly the intelligent part still needs to be created.

A few years ago we had various very good search engine. You could give it a couple of words, and it would use those words to really quickly give a list of results that were related to the words you provided. They improved this search by remembering where people clicked. More clicks meant a result was probable better, so it got a bit higher score.

Now OpenAI has added a new layer to this. It’s tool ChatGPT can understand text, and can tell you something in a natural fashion. You can ask it a question, and it will give you an answer back, just like a normal conversation. Understanding someone is a very complex task. You can ask the same thing in lots of different ways, and small details can be very important or meaningless. The ‘engine’ is trained to know what is important, and what is not. Instead of giving you a list of sites, now you can simply get a summary as an answer. The AI is not storing a huge amount of links, it is reading everything, and storing the information it finds, which is what it uses to answer your question.

We are not there yet, but it is a huge step forward. Understanding language is really difficult, and making it seem ‘natural’ is very hard, but it looks like they really achieved something here. Still, there is no intelligence. For now there is no curiosity, no initiative, no desire. The AI only responds to queries. It remembers what you asked it, but thats it. You can ask it things, and it can tell you things, but it won’t do anything else. It is really good, and clearly the current ‘AI’ is much much better then the ‘old’ search engines.

We can even ask it directly.

Q: are you really intelligent?
A: As an AI language model, I don’t possess a conscious intelligence like humans do. However, I have been trained on vast amounts of data and algorithms to respond to various queries, so I can simulate an intelligent conversation with humans. I can understand natural language and can generate responses based on the information I have been trained on. My abilities are limited to what I have been trained on and what algorithms are available to me.
Q: can you repeat the answer in dutch
A: Als een AI-taalmodel …

Endless advertisements on YouTube

It is getting ridiculous! Years ago (in 2009!) I was already complaining but I never realised it was just the beginning. They were just getting started. Advertisements are now literally everywhere, and you are forced to either pay to reduce the amount, or find other solutions. Just letting it slide, and trying to ignore the ads is nearly impossible, and costs way to much time. Here is a completely legal solution to this problem.

Case study: Youtube has really made a turn for the worst. Not only do you have to endure two or three ads before watching the video you want to see, often times there are ads during the video, and some ads added to the end. If it is a short video you want to see you will be forced to watch much more advertisements than actual content. Sometimes a button will be provided to skip the ads, but this button is hard to press on a smart tv.

Solution for your smart TV: Install SmartTubeNext. This app is free and it offers exactly the same functionality as the YouTube app, except for all the ads. This is how you install this app: (easiest) install Downloader by AFTVnews on your Android TV, open it and enter kutt.it/stn_stable, then read, understand and confirm the security prompts. After this you will have the SmartTubeNext app installed, and you can finally enjoy content without constant interruptions. I did it on our own TV, and I have been so happy ever since! Once you get used to the slightly different interface you will never ever consider going back to the ‘normal’ YouTube app.

Solution for your phone: The YouTube app on my phone was unusable because of the frequent ads. The Brave browser opens YouTube just as normal, but does not download any advertisements. On the phone it does work clearly worse than the YouTube app, but skipping all ads is such a big advantage I feel like for now this is the best option.

Solution for your laptop: I changed to watching the movies in the Brave browser, just like on my phone.

Do you have a good working solution? Please let me know in the comments!

Schoolwork at home

It could have been so easy. It should have been easy, but it is not. I’m talking about the schoolwork our kids get to avoid getting far behind. It looked so logical. Use the internet and just do lots of things from home. It should work, but it has mostly been very frustrating. It is unbelievable that almost everything that could go wrong really does go wrong.

Our kids school uses an app to communicate with the parents. We managed to log in on the app, and then the problems started. The entire interface was customized. No menu, no normal buttons. It took me a couple of days to (by change) figure out how to change the active chapter of a digital book.

Then we have the errors. Of course you can have a typo somewhere, but tasks that need to be returned with incorrect answers required are truly demotivating. Some questions require a true or false, and only allow you to continue if you give the wrong answer.

English. The professor is not a native, but reading simple tests displays a lot of errors that can easily be picked up. It’s not tomato or tomato, but “Tomatoe”. Unbelievable. Out of every three pages with questions one page has one or more errors.

To finish it all off we get PDF’s with additional exercises. For some reason these have huge URLs in them that you need to copy. Manually.

http://xx!$^&*()yy_+`-={zz}|[]:OHNEE-TREKT-HAAR-UIT-HOOFD;JohnnyBoy@www.leiden365.nl/blog/?p=8767&whatallemaalnogmeer&EenHelERieDelTexts/Lekker/Lange/URL

It is clear that the current situation is new for everyone. The idea is to keep the kids occupied so they will not lose to many of the knowledge they have. Next period they will probably try to make it all up. For the parents it is a bit more frustrating. Work during the day and in the evenings solve problems so we can do the schoolwork together.