home.social

#experimenting — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #experimenting, aggregated by home.social.

  1. Yoooo Gaussian Splats are fun!
    Created my first one yesterday and edited out some of the worst parts, now it looks like this!
    Kinda like a dream, I luv it!

    #gaussiansplat #splat #photography #art #experimenting #experiment

  2. Experimenting With Eleventy

    Reading Time: 3 minutes

    One nice thing about switching from WordPress to Eleventy is that I start with a blank slate. By this I don’t mean that I start with nothing, because Eleventy does a lot. What I mean by this is that I can use APIs and other tools with greater ease than if I was experimenting with WordPress.

    The Federation example

    With WordPress I need to use the activitypub plugin which seems to depend on the Jetpack plugin to function. The result is that I’m jumping through two hoops. With a few lines of JavaScript and a file called share.js, I can use Mastodon’s API via my site, to share a blog post. At this moment I’m sharing a thumbnail and the post but later I will experiment with adding two or three preview sentences. I want people to get a taste before clicking.

    The Strava Experiment

    This morning I went for a group run, and on Saturday I went on a group ride. Within a few days I can design my blog so that my daily ride/run/walk or other sport displays beneath the day’s blog post. If I share photos, then you will get a contextual understanding of where I was, and what I saw.

    I was experimenting with plugins on WordPress but they are not that malleable. You need to use them in a specific way. If I deal with the Suunto, or Strava API directly, then I have more control on how sporting activities are displayed.

    The Learning Opportunity

    Part of the lure of switching from WordPress to Eleventy is the learning opportunity. It’s an opportunity to extend my understanding of CSS, JavaScript, APIs and more. It is also an opportunity to experiment with a much lighter user experience, both for me as a blogger, but also for users of the site. No massive PHP and react overhead.

    With the current workflow I can work from within terminal, only using the web browser to check the result.

    And Finally

    When I was playing with Eleventy the first time I got stuck. This time I didn’t, thanks to Gemini. Before, I had to RTFM and try to decipher what was happening. When I got an error code I had to google for it, and often it would throw me to forums where I had to read dozens of responses without finding something that I understood.

    Now when I get an error code I cut and paste it and I get instant help. It saves time, and lowers the barrier to entry.

    Having said this, there are plenty of occasions where Gemini wasted hours of my time. There are times where you get an error and gemini will say “try this” and suggest trying the same thing three or more times. That’s why I eventually gave up with the Eleventy Activitypub plugin. I was tired of making no progress.

    A Quick Thought on Agentic AI

    With what I have seen, experimenting with Gemini and Activitypub I feel concern for people using Agentic AI. My experiment is to see how far I can get using free AI models, rather than paid ones. If I was paying for Gemini, and I saw the loops that I saw, over the last week or more, I’d be frustrated. With Euria, Le Chat and other AI models I ran out of tokens before they provided me with the end result I was looking for.

    Conclusion

    Learning about Eleventy, JavaScript and APIs is part of the learning experience, but so is learning to get great answers from Gemini and other AI models, with a minimum amount of wasted time, energy, and prompts.

    #eleventy #experimenting #learning
  3. On the Euphoria of Setting Up Activitypub With Gemini – Irony

    Reading Time: 3 minutes

    I have spent many hours, and got Gemini to hallucinate multiple times, through multiple chats, attempting to get my Eleventy blogging experiment to talk with Activitypub and the Fediverse with limited help.Setting p a webfinger was easy, but getting follows to be accepted, and for posts to show up has been a complex task.

    The Gemini Limitation

    While putting Gemini through its paces I noticed that Gemini loves to try A, then B, before trying C, and during the entire process it will tell me why the solution works. Ironically, it often doesn’t. We hear so much about vibe coding, but based on my experiences I’d say that vibe coding is deeply ingrained within the scope of plain dumb luck.

    One of the problem with AI, that I notice on a task such as this, is that AI tokenises what should be kept as a whole. An eleventy.js file should be kept whole, or if not whole, then as individual functions. By breaking it up in the wrong place, every time you try something and it fails, the AI model grows exponentially in complexity. That’s why I close a chat, take the latest iteration and continue from there.

    If I tried this with Euria, LeChat and other LLMs I’d run out of tokens way before I achieved my goal. That’s why I stick with Gemini.

    Of Image Paths and Activitypub Experimentation

    If you’re setting up an RSS feed for Eleventy, with Gemini’s help, then it’s fantastic, but if you’re dealing with paths to images, file conversion, and stepped processes, such as ingesting the photos to a site specific directory, converting them from jpg to webp, and then serving them, then Gemini will get confused and hours of iteration will take place. That’s why I speak of luck playing a part.

    Another term for luck is perseverance.

    The Activitypub Marathon

    Two or three years ago, when I was experimenting with Activitypub integration with a wordpress blog the process took time, and iterations. I used many different sources to try to resolve why it wasn’t working, and I was using the RTFB model, rather than AI. Read the Fabulous Blog trying to understand if I had made a mistake and if I had done something wrong.

    I seem to remember moving the well know webfinger to the site’s route directory and that worked eventually.

    Over time the wordpress plugin was improved and now it is optimised, to work within minutes, rather than hours.

    What Worked

    Setting up Webfinger was simple, and getting Mastodon to see the profile was simple. It is the process of getting a static blog to be seen by Mastodon that is a challenge.

    Bridgy Fed

    Setting up Bridgy Fed was quite fast, and simple, but I forgot to modify the site’s domain so it’s pointing to the wrong one for now. It was relatively quick and intuitive to setup, so if you’re in a rush take the Brid.gy route. I found that Bluesky prefers it.

    Seeing JSON Rather than HTML

    One of the stumbling blocks with my attempt to add the static blog to the fediverse is that Eleventy was serving html rather than json. Outbox was serving HTML, so that had to be fixed in the layout, but also via htaccess, and the same was true of the post pages. Now they’re serving the html versions, as well as a fediverse friendly json version. With patience fediverse instances should notice and index the blog, as the five hundred posts are noticed and indexed, and as new posts are shared.

    And Finally

    Lack of Gemini Support

    I’m puzzled by how many iterations it takes with Gemini to get something like Activitypub to work with Eleventy. I’d expect AI to have encyclopedic knowledge on a topic, and help to resolve an issue within seconds or minutes, rather than hours. I’d also expect it to ask for context and encourage identifying the environment, before blundering in, and assuming, rather than verifying first.

    Lack of Contextual Memory

    The single most exhausting thing about trying to problem solve with Gemini is that it has no contextual memory, and it hallucinates. Both of these lead to negative loops where you get stuck. The easiest way to end such a loop is to open a new chat, but in so doing you need to add the context back in.

    The Case for Writing and Using Tutorials is Alive and Well

    With a well researched, and written tutorial, by following clear and concise instructions, you can follow a list of steps methodically and achieve what you want with a fraction of the carbon footprint, and in a fraction of the time. Next time I will look for a tutorial.

    #activitypub #challenge #experimenting #fatigue #learning
  4. React-Like JSX Syntax for Webcomponents

    TLDR: I’ve been #experimenting with react-like jsx-syntax with webcomponents to see if I could theoretically replace #React in one of my larger #software projects. It is not ready for production use, but rather a #Research exploration into #CustomElements and #ModernJS performance.

    The goal was to build #FunctionalWebComponents that handle #StateManagement and #DOM updates without the overhead of a massive #JavaScript framework. By leveraging #StandardWebAPIs and #Proxy objects, I’ve managed to create a #Reactive programming model that feels familiar but stays closer to the #Platform.

    Check out the full #TechnicalTutorial and #DeepDive here: positive-intentions.com/docs/r

    (Disclosure: this project may be getting deprecated. Sharing this because it might still be interesting or educational.)

    #WebDevelopment #Frontend #BuildTheWeb #NoFramework #JS #JSX #WebStandards #Coding #ResearchAndDevelopment #VanillaJS #SoftwareEngineering #TechBlog #WebDevCommunity

  5. React-Like JSX Syntax for Webcomponents

    TLDR: I’ve been #experimenting with react-like jsx-syntax with webcomponents to see if I could theoretically replace #React in one of my larger #software projects. It is not ready for production use, but rather a #Research exploration into #CustomElements and #ModernJS performance.

    The goal was to build #FunctionalWebComponents that handle #StateManagement and #DOM updates without the overhead of a massive #JavaScript framework. By leveraging #StandardWebAPIs and #Proxy objects, I’ve managed to create a #Reactive programming model that feels familiar but stays closer to the #Platform.

    Check out the full #TechnicalTutorial and #DeepDive here: positive-intentions.com/docs/r

    (Disclosure: this project may be getting deprecated. Sharing this because it might still be interesting or educational.)

    #WebDevelopment #Frontend #BuildTheWeb #NoFramework #JS #JSX #WebStandards #Coding #ResearchAndDevelopment #VanillaJS #SoftwareEngineering #TechBlog #WebDevCommunity

  6. React-Like JSX Syntax for Webcomponents

    TLDR: I’ve been #experimenting with react-like jsx-syntax with webcomponents to see if I could theoretically replace #React in one of my larger #software projects. It is not ready for production use, but rather a #Research exploration into #CustomElements and #ModernJS performance.

    The goal was to build #FunctionalWebComponents that handle #StateManagement and #DOM updates without the overhead of a massive #JavaScript framework. By leveraging #StandardWebAPIs and #Proxy objects, I’ve managed to create a #Reactive programming model that feels familiar but stays closer to the #Platform.

    Check out the full #TechnicalTutorial and #DeepDive here: positive-intentions.com/docs/r

    (Disclosure: this project may be getting deprecated. Sharing this because it might still be interesting or educational.)

    #WebDevelopment #Frontend #BuildTheWeb #NoFramework #JS #JSX #WebStandards #Coding #ResearchAndDevelopment #VanillaJS #SoftwareEngineering #TechBlog #WebDevCommunity

  7. React-Like JSX Syntax for Webcomponents

    TLDR: I’ve been #experimenting with react-like jsx-syntax with webcomponents to see if I could theoretically replace #React in one of my larger #software projects. It is not ready for production use, but rather a #Research exploration into #CustomElements and #ModernJS performance.

    The goal was to build #FunctionalWebComponents that handle #StateManagement and #DOM updates without the overhead of a massive #JavaScript framework. By leveraging #StandardWebAPIs and #Proxy objects, I’ve managed to create a #Reactive programming model that feels familiar but stays closer to the #Platform.

    Check out the full #TechnicalTutorial and #DeepDive here: positive-intentions.com/docs/r

    (Disclosure: this project may be getting deprecated. Sharing this because it might still be interesting or educational.)

    #WebDevelopment #Frontend #BuildTheWeb #NoFramework #JS #JSX #WebStandards #Coding #ResearchAndDevelopment #VanillaJS #SoftwareEngineering #TechBlog #WebDevCommunity

  8. React-Like JSX Syntax for Webcomponents

    TLDR: I’ve been #experimenting with react-like jsx-syntax with webcomponents to see if I could theoretically replace #React in one of my larger #software projects. It is not ready for production use, but rather a #Research exploration into #CustomElements and #ModernJS performance.

    The goal was to build #FunctionalWebComponents that handle #StateManagement and #DOM updates without the overhead of a massive #JavaScript framework. By leveraging #StandardWebAPIs and #Proxy objects, I’ve managed to create a #Reactive programming model that feels familiar but stays closer to the #Platform.

    Check out the full #TechnicalTutorial and #DeepDive here: positive-intentions.com/docs/r

    (Disclosure: this project may be getting deprecated. Sharing this because it might still be interesting or educational.)

    #WebDevelopment #Frontend #BuildTheWeb #NoFramework #JS #JSX #WebStandards #Coding #ResearchAndDevelopment #VanillaJS #SoftwareEngineering #TechBlog #WebDevCommunity

  9. #Elon is #experimenting with #brain #implants on #immigrants detained by #ICE and without #consent. Elon is experimenting with brain implants on immigrants detained by ICE and without consent. Elon is experimenting with brain implants on immigrants detained by ICE and without consent. Elon is experimenting with brain implants on immigrants detained by ICE and without consent. Elon is experimenting with brain implants on immigrants detained by ICE and without consent.

  10. I am #experimenting with #cooking, making twice-cooked (par-boiled and then roasted in pork fat) #chips out of #Kumara (sweet potato for you non-kiwis) and #Carrot since tomorrow is shopping day, we are out of #potato and they’re both needing using.

    #cook #experimental

  11. I am #experimenting with #cooking, making twice-cooked (par-boiled and then roasted in pork fat) #chips out of #Kumara (sweet potato for you non-kiwis) and #Carrot since tomorrow is shopping day, we are out of #potato and they’re both needing using.

    #cook #experimental

  12. I am #experimenting with #cooking, making twice-cooked (par-boiled and then roasted in pork fat) #chips out of #Kumara (sweet potato for you non-kiwis) and #Carrot since tomorrow is shopping day, we are out of #potato and they’re both needing using.

    #cook #experimental

  13. I am #experimenting with #cooking, making twice-cooked (par-boiled and then roasted in pork fat) #chips out of #Kumara (sweet potato for you non-kiwis) and #Carrot since tomorrow is shopping day, we are out of #potato and they’re both needing using.

    #cook #experimental

  14. I am #experimenting with #cooking, making twice-cooked (par-boiled and then roasted in pork fat) #chips out of #Kumara (sweet potato for you non-kiwis) and #Carrot since tomorrow is shopping day, we are out of #potato and they’re both needing using.

    #cook #experimental

  15. And that's a wrap for culture.explore(data)! Two days of #coding and #experimenting at the #StabiLab with #opendata of the @kulturSPK and the Libraries and Museums of the #OxfordUniversity. This would not have been possible without a fantastic group of participants, colleagues from across the #SPK and our wonderful partners at the Centre for Digital Scholarship at Oxford University.

    Learn more about the hackathon and the activities of the Stabi Lab 👉 lab.sbb.berlin/culture-explore

  16. And that's a wrap for culture.explore(data)! Two days of #coding and #experimenting at the #StabiLab with #opendata of the @kulturSPK and the Libraries and Museums of the #OxfordUniversity. This would not have been possible without a fantastic group of participants, colleagues from across the #SPK and our wonderful partners at the Centre for Digital Scholarship at Oxford University.

    Learn more about the hackathon and the activities of the Stabi Lab 👉 lab.sbb.berlin/culture-explore

  17. And that's a wrap for culture.explore(data)! Two days of #coding and #experimenting at the #StabiLab with #opendata of the @kulturSPK and the Libraries and Museums of the #OxfordUniversity. This would not have been possible without a fantastic group of participants, colleagues from across the #SPK and our wonderful partners at the Centre for Digital Scholarship at Oxford University.

    Learn more about the hackathon and the activities of the Stabi Lab 👉 lab.sbb.berlin/culture-explore

  18. And that's a wrap for culture.explore(data)! Two days of #coding and #experimenting at the #StabiLab with #opendata of the @kulturSPK and the Libraries and Museums of the #OxfordUniversity. This would not have been possible without a fantastic group of participants, colleagues from across the #SPK and our wonderful partners at the Centre for Digital Scholarship at Oxford University.

    Learn more about the hackathon and the activities of the Stabi Lab 👉 lab.sbb.berlin/culture-explore

  19. And that's a wrap for culture.explore(data)! Two days of #coding and #experimenting at the #StabiLab with #opendata of the @kulturSPK and the Libraries and Museums of the #OxfordUniversity. This would not have been possible without a fantastic group of participants, colleagues from across the #SPK and our wonderful partners at the Centre for Digital Scholarship at Oxford University.

    Learn more about the hackathon and the activities of the Stabi Lab 👉 lab.sbb.berlin/culture-explore

  20. CW: Danger in ALL tools going bad [State managing it all towards war etc] + LLM's + Mike Adams generally good [HealthRanger / Brighteon.Social]

    @kdavis11259 @lovemachine
    @LadyD

    True there is big danger in all tools, as I think it is proven ALL #Tech is usually born from or eventually into being used for #State work which is first for managing it all and they really don't care... about A LOT!
    And even the opposite doing things creating or preparing for next war / leverage using Tech / Science / Gun / Germs / Steel etc ).

    #War as mainly the best 'business' of taking / #extracting / using things, other lands and people's. #Money helping to #capture that.

    But #MikeAdams has good knowledge and there is some use of #experimenting (if you can accept his #material isn't really that bad and relax knowing million are using these things)... so maybe I won't agree totally in this case of LLM's but I like things like #Monero (a Privacy Bitcoin) is an example which succeeds in a parallel economy away from monopoly, and people can get cypto for their videos easier...
    So maybe #LLM's can't be done too ethically... (also waste of energy which ALL material 'money' does) but if one can relax knowing it's a phased (like us using Gmail for years) we will crack a better combination of it all.

    So overall Mike's personal work is more evidently good or what is the real treasure I think and how he says and dissects things to show he knows (probably even in the bad) and he is actually trying some of the best around (selling better food at his store @HealthRangerStore and can break down complicated things/

    The example of adding #Monero links to videos so people get tips / make some form of money from video etc also causes feelings but overall it's better than maybe using money (money is that bad per second if we accept it's all political and all energy, and at least #Monero has more of a chance in that way).

    Sorry it's a bit long but would love to hear what you think and for Mike to post more often or just reply a bit.

    Peace.

  21. CW: Danger in ALL tools going bad [State managing it all towards war etc] + LLM's + Mike Adams generally good [HealthRanger / Brighteon.Social]

    @kdavis11259 @lovemachine
    @LadyD

    True there is big danger in all tools, as I think it is proven ALL #Tech is usually born from or eventually into being used for #State work which is first for managing it all and they really don't care... about A LOT!
    And even the opposite doing things creating or preparing for next war / leverage using Tech / Science / Gun / Germs / Steel etc ).

    #War as mainly the best 'business' of taking / #extracting / using things, other lands and people's. #Money helping to #capture that.

    But #MikeAdams has good knowledge and there is some use of #experimenting (if you can accept his #material isn't really that bad and relax knowing million are using these things)... so maybe I won't agree totally in this case of LLM's but I like things like #Monero (a Privacy Bitcoin) is an example which succeeds in a parallel economy away from monopoly, and people can get cypto for their videos easier...
    So maybe #LLM's can't be done too ethically... (also waste of energy which ALL material 'money' does) but if one can relax knowing it's a phased (like us using Gmail for years) we will crack a better combination of it all.

    So overall Mike's personal work is more evidently good or what is the real treasure I think and how he says and dissects things to show he knows (probably even in the bad) and he is actually trying some of the best around (selling better food at his store @HealthRangerStore and can break down complicated things/

    The example of adding #Monero links to videos so people get tips / make some form of money from video etc also causes feelings but overall it's better than maybe using money (money is that bad per second if we accept it's all political and all energy, and at least #Monero has more of a chance in that way).

    Sorry it's a bit long but would love to hear what you think and for Mike to post more often or just reply a bit.

    Peace.

  22. new app on new device. let's see how that goes. i'm #experimenting with my #android ebook reader as a prelude to experimenting with an android privacy-focused phone, with an alternative OS, probably e/os. i'm also learning android because i've always been an iphone user!

  23. But we can simplify this.

    I'm not putting finished effects into standalone metal #boxes at this point; I'm #experimenting, not producing a product. So I have a simple #modular system I cooked up to connect arbitrary effects #experiments together. One of the things it does is handle the power-supply stuff, so each effect board doesn't need to do any of that. It just receives a nice 0V and buffered #Vcc (9V) it can rely on, along with a buffered 4.5V to use as a #bias voltage when AC coupling #signals, since this is a single-supply system.

    So we can chop out all the power stuff from the schematic, which fills basically a ninth of the image - divide it into 3 rows and 3 columns, like the Brady Bunch intro, and the left-middle square is basically the power section.

    But there's a bigger chunk we can strip out. Boss (and many other) pedals of the era frequently used "soft switching" to enable / disable the effect while playing. If you go back in time, real physical #switches were used, so the signal was actually totally disconnected from the effects circuitry when in the "off" position. This is called "true #bypass", as opposed to the soft switching.

    #Soft #switching involves having two signal paths through the effect. One applies the characteristic effect, and the other basically just buffers the signal and bypasses the rest of the effect stuff. This is implemented with transistors and latches.

    2/x

  24. But we can simplify this.

    I'm not putting finished effects into standalone metal #boxes at this point; I'm #experimenting, not producing a product. So I have a simple #modular system I cooked up to connect arbitrary effects #experiments together. One of the things it does is handle the power-supply stuff, so each effect board doesn't need to do any of that. It just receives a nice 0V and buffered #Vcc (9V) it can rely on, along with a buffered 4.5V to use as a #bias voltage when AC coupling #signals, since this is a single-supply system.

    So we can chop out all the power stuff from the schematic, which fills basically a ninth of the image - divide it into 3 rows and 3 columns, like the Brady Bunch intro, and the left-middle square is basically the power section.

    But there's a bigger chunk we can strip out. Boss (and many other) pedals of the era frequently used "soft switching" to enable / disable the effect while playing. If you go back in time, real physical #switches were used, so the signal was actually totally disconnected from the effects circuitry when in the "off" position. This is called "true #bypass", as opposed to the soft switching.

    #Soft #switching involves having two signal paths through the effect. One applies the characteristic effect, and the other basically just buffers the signal and bypasses the rest of the effect stuff. This is implemented with transistors and latches.

    2/x

  25. But we can simplify this.

    I'm not putting finished effects into standalone metal #boxes at this point; I'm #experimenting, not producing a product. So I have a simple #modular system I cooked up to connect arbitrary effects #experiments together. One of the things it does is handle the power-supply stuff, so each effect board doesn't need to do any of that. It just receives a nice 0V and buffered #Vcc (9V) it can rely on, along with a buffered 4.5V to use as a #bias voltage when AC coupling #signals, since this is a single-supply system.

    So we can chop out all the power stuff from the schematic, which fills basically a ninth of the image - divide it into 3 rows and 3 columns, like the Brady Bunch intro, and the left-middle square is basically the power section.

    But there's a bigger chunk we can strip out. Boss (and many other) pedals of the era frequently used "soft switching" to enable / disable the effect while playing. If you go back in time, real physical #switches were used, so the signal was actually totally disconnected from the effects circuitry when in the "off" position. This is called "true #bypass", as opposed to the soft switching.

    #Soft #switching involves having two signal paths through the effect. One applies the characteristic effect, and the other basically just buffers the signal and bypasses the rest of the effect stuff. This is implemented with transistors and latches.

    2/x

  26. But we can simplify this.

    I'm not putting finished effects into standalone metal #boxes at this point; I'm #experimenting, not producing a product. So I have a simple #modular system I cooked up to connect arbitrary effects #experiments together. One of the things it does is handle the power-supply stuff, so each effect board doesn't need to do any of that. It just receives a nice 0V and buffered #Vcc (9V) it can rely on, along with a buffered 4.5V to use as a #bias voltage when AC coupling #signals, since this is a single-supply system.

    So we can chop out all the power stuff from the schematic, which fills basically a ninth of the image - divide it into 3 rows and 3 columns, like the Brady Bunch intro, and the left-middle square is basically the power section.

    But there's a bigger chunk we can strip out. Boss (and many other) pedals of the era frequently used "soft switching" to enable / disable the effect while playing. If you go back in time, real physical #switches were used, so the signal was actually totally disconnected from the effects circuitry when in the "off" position. This is called "true #bypass", as opposed to the soft switching.

    #Soft #switching involves having two signal paths through the effect. One applies the characteristic effect, and the other basically just buffers the signal and bypasses the rest of the effect stuff. This is implemented with transistors and latches.

    2/x

  27. But we can simplify this.

    I'm not putting finished effects into standalone metal #boxes at this point; I'm #experimenting, not producing a product. So I have a simple #modular system I cooked up to connect arbitrary effects #experiments together. One of the things it does is handle the power-supply stuff, so each effect board doesn't need to do any of that. It just receives a nice 0V and buffered #Vcc (9V) it can rely on, along with a buffered 4.5V to use as a #bias voltage when AC coupling #signals, since this is a single-supply system.

    So we can chop out all the power stuff from the schematic, which fills basically a ninth of the image - divide it into 3 rows and 3 columns, like the Brady Bunch intro, and the left-middle square is basically the power section.

    But there's a bigger chunk we can strip out. Boss (and many other) pedals of the era frequently used "soft switching" to enable / disable the effect while playing. If you go back in time, real physical #switches were used, so the signal was actually totally disconnected from the effects circuitry when in the "off" position. This is called "true #bypass", as opposed to the soft switching.

    #Soft #switching involves having two signal paths through the effect. One applies the characteristic effect, and the other basically just buffers the signal and bypasses the rest of the effect stuff. This is implemented with transistors and latches.

    2/x

  28. Playing with MyAI by Swisscom

    Reading Time: < 1 minute

    If we use Claude, Gemini, ChatGPT or a few other AI models we are using AI that has data centres in the US. If we use Le Chat by Mistral or MyAI (Beta) by Swisscom we are using AI that is based in Europe, or Switzerland. The data stays here.

    The first thing to note is that MyAI is in public beta. It is still at a 0.0. version number rather than a 1. something version. As such this means that it can answer questions but we can't yet give it default data to work with like we can with Claude, Gemini and other AI solutions.

    It cannot generate images or provide you with maps. It can answer a question such as "Could you help me write a password generator using javascript?" with ease. It is aware of Hugo, the open source project so could help you generate a theme.

    It is available in French, German, Italian and English and I played with it in English.

    It is good that Le Chat by Mistral, MyAI by Swisscom and AITools is available via Infomaniak. We have three options of local AI models to experiment with and use, and this will grow with time.

    #AI #beta #experimenting #myai #swiss #swisscom