Salamander

  • 4 Posts
  • 86 Comments
Joined 3 years ago
Cake day: December 19th, 2021
  • Salamander@mander.xyztoPrivacy@lemmy.ml•"They already have your data"
    6·
    2 months ago

    If they can send me over the second half of my thesis I would appreciate it enormously! 😀

    The analytics tools that I am personally uncomfortable with involve dynamic, changing forms of data. I run GPSLogger on my phone (without a SIM card) and continuously log the GPS data to a text file. This data is then synced to my computer when WiFi is available. I can display this data on a map using gpx-viewer, and show very detailed tracking data of myself.

    I have explored this map with some friends/family. They get to see a time-stamped movie of my life - my trips to work, to the shop, when I go out, if I go on a trip, etc. The data displayed in this manner is somewhat intimate, personal information. Anyone I have shown this to has said that they would not be so comfortable with such a map of their lives existing… Well, if they are carrying a active phone with a SIM card, it does.

    To think that a company like Google can own such a map for a very large number of people makes me uncomfortable. On top of that, each of those map trajectories can be associated with an individual and their personality… They have the ability to pick out specific trajectories on the basis of the political ideologies or shopping behaviors of the personas behind them. This is extreme. I am of the opinion that the convenience afforded by a these technologies does not justify the allocation of that super-power to the companies that enable the technology.

    A few years ago Facebook enabled a “Graph search” feature. This allowed users to create search queries such as"Friends of friends of X who like the page “X” and went to school near Z". That tool seemed super cool on the surface, but it quickly became obvious how something like that could be easily exploited. Later on in Snowden’s book I learned about XKeyscore from the NSA, which is like an extra-powerful no-consent-needed graph search that is available to some people. This is not just targeted ads.

    I guess that what I am trying to convey is… For me, making the privacy-conscious choice is about not contributing to the ecosystem of very concrete tools that give super-powers to groups of people that may not have my best interest in mind. In my mind it is something very tangible and concrete, and I find many of those convenience tradeoffs to be clearly worth it.

  • Salamander@mander.xyztoAsklemmy@lemmy.ml•What's your favourite Youtube channel most people probably haven't heard of?
    3·
    2 months ago

    Fresh from the Farm Fungi - he is a mushroom farmer from Colorado. He has a ton of valuable information on growing mushrooms and running a business. He also has a few series of videos on very interesting experiments such as growing boletus, morelles, and cordyceps.

    Microbehunter - he is a biology teacher that runs a microscope channel. His videos are very useful for learning the basics of microscopy.

    Huygen Optics - I’m not sure about this guy’s background. He worked in R&D for Phillips in the 90s and he knows a lot about optics and chemistry, but I don’t know much more. He has built some equipment in has garage for sputtering metals on surfaces and has some pretty cool videos.

    MissOrchidGirl - she is more popular than the others. She has great info about caring for orchids and a fantastic orchid collection.

    Ben Felix - he is a portfolio manager with very solid financial advice. He supports his claims with research articles.

  • Salamander@mander.xyztoAsklemmy@lemmy.ml•How does the profanity filter work?
    7·
    2 months ago

    The “Slur filter” is a server setting. The filter makes use of a “regex” (a text matching algorithm) to automatically remove any text that matches those words. An admin needs to explicitly set the rules for that regex. The regex does not take language into account, it is a simple text matching algorithm.

    The box is in the Admin settings page and looks like this:

    I know that lemmy.ml makes use of a strict set of regex rules. The translation of the french word for “late” matches an ableist slur in English, and so it is removed by lemmy.ml. I am not sure about whether you can check regex for each individual server, but I believe that most instances don’t filter that specific word out.

    EDIT: Ah, I found out how to check the regex. You can check an instance’s regex by going to the the URL https://{instance}.{TLD}/api/v3/site and looking for “slur_filter_regex”. For example, for lemmy.ml you would go to:

    https://lemmy.ml/api/v3/site

  • Salamander@mander.xyztoAsklemmy@lemmy.ml•What is common way to detect backend AI model or AI provider?
    21·
    3 months ago

    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!
  • Salamander@mander.xyzOPtoOpen Source@lemmy.ml•Rethinking open source generative AI: open washing and the EU AI Act
    5·
    7 months ago

    I did not know of the term “open washing” before reading this article. Unfortunately it does seem like the pending EU legislation on AI has created a strong incentive for companies to do their best to dilute the term and benefit from the regulations.

    There are some paragraphs in the article that illustrate the point nicely:

    In 2024, the AI landscape will be shaken up by the EU’s AI Act, the world’s first comprehensive AI law, with a projected impact on science and society comparable to GDPR. Fostering open source driven innovation is one of the aims of this legislation. This means it will be putting legal weight on the term “open source”, creating only stronger incentives for lobbying operations driven by corporate interests to water down its definition.

    […] Under the latest version of the Act, providers of AI models “under a free and open licence” are exempted from the requirement to “draw up and keep up-to-date the technical documentation of the model, including its training and testing process and the results of its evaluation, which shall contain, at a minimum, the elements set out in Annex IXa” (Article 52c:1a). Instead, they would face a much vaguer requirement to “draw up and make publicly available a sufficiently detailed summary about the content used for training of the general-purpose AI model according to a template provided by the AI Office” (Article 52c:1d).

    If this exemption or one like it stays in place, it will have two important effects: (i) attaining open source status becomes highly attractive to any generative AI provider, as it provides a way to escape some of the most onerous requirements of technical documentation and the attendant scientific and legal scrutiny; (ii) an as-yet unspecified template (and the AI Office managing it) will become the focus of intense lobbying efforts from multiple stakeholders (e.g., [12]). Figuring out what constitutes a “sufficiently detailed summary” will literally become a million dollar question.

    Thank you for pointing out Grayjay, I had not heard of it. I will look into it.

  • Salamander@mander.xyztoAsklemmy@lemmy.ml•What would you bring to an adult show and tell?
    34·
    11 months ago

    If the timing is right, I would bring a mushroom grow bag with mushrooms sprouting.

    If not… probably my radiacode gamma spectrometer and some of my radioactive items. Maybe a clock with radium painted dials and a piece of trinitite. I think that there are many different points of discussion that can be of interest to a broad audience (radioactivity, spectroscopy, electronics, US labor law story of the radium girls, nuclear explosions, background radiation… etc). As a bonus I can bring a UV flash light and show the radium fluorescence. Adults love UV flash lights.