tfowinder

@tfowinder@lemmy.ml

• ⁨Comment⁩ on ⁨Trump’s Defiance of TikTok Ban Prompted Immunity Promises to 10 Tech Companies⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  ELI5 please, went over my head as I am not following this issue.

• ⁨Comment⁩ on ⁨ICEBlock climbs to the top of the App Store charts after officials slam it⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  Expected this after recent news articles criticizing it for hurting ICE officers.

• ⁨Comment⁩ on ⁨$219 Springer Nature book on machine learning was written with a chatbot⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  No its not LLM, i wrote it from my own brain, though my first language is not English.

• ⁨Comment⁩ on ⁨$219 Springer Nature book on machine learning was written with a chatbot⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  Hmm Interesting, seems your Model is hallucinating a lot, maybe try improving your system prompt. I have a deepseek-ai_DeepSeek-R1-Distill-Qwen-1.5B Running locally. Here is my output for the Orignal Comment

  The article discusses the perception of a book as trash due to the author’s use of LLM without informing readers. The author highlights the benefits of using LLMs, such as saving time and improving productivity, by suggesting that using locally deployed LLMs can significantly enhance the summarization process. The article also warns against the misuse of LLMs, emphasizing the importance of verifying information. The author concludes that relying on LLMs can surpass human capabilities when combined with personal knowledge. Key Details: The article’s main points are:

  1. The book is perceived as trash due to LLM usage without reader notification.
  2. LLMs save time and improve productivity.
  3. Using locally deployed LLMs for summarization is effective.
  4. Misuse of LLMs can lead to false information.
  5. Combining LLMs with personal knowledge enhances quality.

  I use the following prompt before article

  You are a concise summarization AI. Follow these rules:

  • NEVER exceed 4 sentences or 150 words.
  • Use this format:
    "Summary: [2-sentence core idea].
    Key Details: [3–4 bullet points]."
  • Omit examples, disclaimers, or fluff.

• ⁨Comment⁩ on ⁨Trump Team Has Full Meltdown Over CNN Story on ICE-Tracking App⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  Its totally possible to send notification without having user account, see firebase.

• ⁨Comment⁩ on ⁨Trump Team Has Full Meltdown Over CNN Story on ICE-Tracking App⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  While this is true, most people are not so tech savvy, maybe giving an option to mask app Icon to user choice can help it hide better.

• ⁨Comment⁩ on ⁨$219 Springer Nature book on machine learning was written with a chatbot⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  Okay so hear me out on this. The book mentioned in this article is definitely a trash, the author used LLM without informing readers, which is why most people feel the are being scammed and express feelings of frustration and hate.

  I personally have deployed LLMs on my local machines and used them for variety of things such as Summarize news and Articles, Coding, Image Generation, etc and I have to be honest it is really really impressive technology. Any author who takes assistance from LLM would be hyper-productive compared to someone who does all the labour themselves. I used to take hours to read a broad area of knowledge and then deep dive in intrested topics. When LLMs generate summary and you can decide weather to read the source yourself or not is a big time saver and productivity boost. Of course this can be abused by someone who trusts LLMs too much and don’t again verifies what they read, it can give false information but that’s not how they are supposed to be used.

  These language models are really good at creating summaries. I use a locally deployed LLM to read summaries of Articles and then if I feel interested I read the entire article end to end from original source. In Almost every case the summary is spot on without it missing any important points or topics, heck I have created system prompt so that it tries to give hot takes and nuanced perspectives from the article and it impresses me sometimes giving me a new perspective which I would have not thought otherwise.

  I am convinced that using LLM along with your own knowledge always surpasses the quality of your work if someone with your same capability generates work without taking assistance of a LLM.

• ⁨Comment⁩ on ⁨xkcd #3109: Dehumidifier⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  That’s really interesting, i was looking into Zigbee plug documentation, could not find if i can program them myself. Do i need to use their propritery app for whatever it does ?

  How did you integrate the plug into existing home automation system ?

• ⁨Comment⁩ on ⁨xkcd #3109: Dehumidifier⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  The Toilet has alexa built into it

• ⁨Comment⁩ on ⁨xkcd #3109: Dehumidifier⁩ ⁨⁨2⁩ ⁨weeks⁩ ago⁩:

  American toilets get Singing toilets before bidets.

• ⁨Comment⁩ on ⁨Against AI: An Open Letter From Writers to Penguin Random House, HarperCollins, Simon & Schuster, Hachette Book Group, Macmillan, and all other publishers of America⁩ ⁨⁨3⁩ ⁨weeks⁩ ago⁩:

  That’s not how capitalism works my friend

• ⁨Comment⁩ on ⁨How streaming changed the way you watch TV⁩ ⁨⁨3⁩ ⁨weeks⁩ ago⁩:

  Don’t worry, Netflix planning to add interstitial ads to their low tier plans

• ⁨Comment⁩ on ⁨Yes, this is what people did back then⁩ ⁨⁨3⁩ ⁨weeks⁩ ago⁩:

  Go and have a taste of McDonalds if its the same

• ⁨Comment⁩ on ⁨It is what it is⁩ ⁨⁨3⁩ ⁨weeks⁩ ago⁩:

  Firefox’s main funding was was ? I think it still is

• ⁨Comment⁩ on ⁨Your TV Is Spying On You⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  There has to be a youtube guide to giving WiFi Lobotomy

• ⁨Comment⁩ on ⁨Your TV Is Spying On You⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  How old is it ? Which one did you buy

• ⁨Comment⁩ on ⁨Your TV Is Spying On You⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  HEC feature enables IP-based applications over HDMI and provides a bidirectional Ethernet communication at 100 Mbit/s

  I think the bandwidth is too slow for HD/4K Streams.

  I am sure the 100 Mbit/s must also be theoretical maximum, i would be impressed if practical cables supports even half the orignal specs

• ⁨Comment⁩ on ⁨Why is the manosphere on the rise? UN Women sounds the alarm over online misogyny⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  This is a most excellent place for technology news and articles.

  I personally browse this community for tech news and updates, this seems more like an American societal problem. Not something happening all around the world. Personally i won’t be interested in reading the article because I live in Asia and the society here is completely different. This kind of misogyny is not seen by me.

• ⁨Comment⁩ on ⁨Child Welfare Experts Horrified by Mattel's Plans to Add ChatGPT to Toys After Mental Health Concerns for Adult Users⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  They already are spying using [techxplore.com/…/2024-08-smart-toys-spying-kids-p…](Smart Toys)

• ⁨Comment⁩ on ⁨Child Welfare Experts Horrified by Mattel's Plans to Add ChatGPT to Toys After Mental Health Concerns for Adult Users⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  This is going to be horrible !!

• ⁨Comment⁩ on ⁨Why is the manosphere on the rise? UN Women sounds the alarm over online misogyny⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  Nothing against the article but why is this in /c/Technology ?

  If something has word online/Internet on it does not mean it has something to do with technology.

• ⁨Comment⁩ on ⁨The end of Windows 10 is approaching, so it's time to consider Linux and LibreOffice⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  I don’t understand how can critical buisness machines which work perfectly fine be switched to windows 11?

  We have a machine at work which is beefy and works as a server and backups for many many years on windows 10. Why the hell should I upgrade my buisness critical system ?? Why would I take my risk breaking stuff. I am sure there are millions of critical systems running gon windows 10 which should not be distribed at any means, what would Microsoft do about them.

• ⁨Comment⁩ on ⁨A 3-tonne, $1.5 billion satellite to watch Earth’s every move is set to launch this week⁩ ⁨⁨4⁩ ⁨weeks⁩ ago⁩:

  This is really cool.

  Anyone know where can I publically find satellite data which is regularly updated, for hobby projects.

• ⁨Comment⁩ on ⁨Been a good couple of years⁩ ⁨⁨5⁩ ⁨weeks⁩ ago⁩:

  Would have to start from scratch as RIF was not open source and now abandoned as far as I know.

• ⁨Comment⁩ on ⁨Been a good couple of years⁩ ⁨⁨5⁩ ⁨weeks⁩ ago⁩:

  Just curious, why people avoid lemmy.ml i joined this beliveing its run by the lemmy devs so should be safest.

• ⁨Comment⁩ on ⁨Been a good couple of years⁩ ⁨⁨5⁩ ⁨weeks⁩ ago⁩:

  RIF still works with some twaks, you need to patch it with an API key similar to youtube vanced and then it works. though some people report the method stopped working recently. Any way its a lost cause.

• ⁨Comment⁩ on ⁨Been a good couple of years⁩ ⁨⁨5⁩ ⁨weeks⁩ ago⁩:

  This made me curious, how much funding does it actually require for maintining reasonable amount of users in the long term ?

• ⁨Comment⁩ on ⁨Been a good couple of years⁩ ⁨⁨5⁩ ⁨weeks⁩ ago⁩:

  Exactly !!

  Miss RIF so much.

• ⁨Comment⁩ on ⁨Best way to get IPv4 connectivity to my self-hosted services⁩ ⁨⁨5⁩ ⁨weeks⁩ ago⁩:

  I have a VPS hosted on Digital ocean with Nginx running as proxy, I use openvpn to connect to the VPS and access all my services over the VPS ip address.

  I own a domain and forward all the requests from my domain to the Home server IP from my VPS, very useful because I can use different subdomains for different services all on port 80 or 443 even though the service is running on random port.

• ⁨Comment⁩ on ⁨Backup for important files/pictures?⁩ ⁨⁨1⁩ ⁨month⁩ ago⁩:

  Need to give synthing a try