g33kphr33k's recent activity

  1. Comment on Cargo ship hits major bridge in Baltimore, triggering collapse (gifted link) in ~transport

    g33kphr33k
    Link Parent
    Sounds like a bad design at that length. Thank you for the explanation.

    Sounds like a bad design at that length.

    Thank you for the explanation.

    4 votes
  2. Comment on What have you been eating, drinking, and cooking? in ~food

    g33kphr33k
    Link Parent
    You are my opposite. I love cooking. I love eating. Food is delicious. I've met a couple of people that could simply give up food tomorrow and live without the taste, only to find out that both...

    You are my opposite. I love cooking. I love eating. Food is delicious.

    I've met a couple of people that could simply give up food tomorrow and live without the taste, only to find out that both had an issue with either palette or smell which took away their enjoyment. It might be worth getting that checked.

    However, if you can smell and taste fine and you simply find food "meh", there are so many Soylent options and alternatives on the market these days it's crazy. From pre-packaged bars and drinks to straight mix-and-drink powders. At least you'd get everything you need and not have to think about it.

    4 votes
  3. Comment on Bad Boys: Ride or Die | Official trailer in ~movies

    g33kphr33k
    Link
    I'm going to go opposite to the other posters - why can they not just leave things alone. Stop dragging out old IP and just make a new movie with new people. It's safe to say I didn't enjoy the...

    I'm going to go opposite to the other posters - why can they not just leave things alone. Stop dragging out old IP and just make a new movie with new people.

    It's safe to say I didn't enjoy the last movie, it's nothing compared to the original.

    11 votes
  4. Comment on Cargo ship hits major bridge in Baltimore, triggering collapse (gifted link) in ~transport

    g33kphr33k
    Link Parent
    Get ready for all of the videos explaining why the whole thing fell. That was the biggest part for me. A bridge constructed in sections should not concertina into the sea like that. I would have...

    Get ready for all of the videos explaining why the whole thing fell. That was the biggest part for me.

    A bridge constructed in sections should not concertina into the sea like that. I would have expected it to break at points.

    5 votes
  5. Comment on How do you store ”loose” tech hardware? in ~tech

    g33kphr33k
    Link Parent
    We share the same spirit.

    We share the same spirit.

    2 votes
  6. Comment on The Crow (2024) | Official trailer in ~movies

    g33kphr33k
    Link
    The Crow Original movie, the soundtrack and the movie music score were all amazing and pretty much shaped a large chunk of me in the 90s. I can get behind this remake/retelling of the story as...

    The Crow Original movie, the soundtrack and the movie music score were all amazing and pretty much shaped a large chunk of me in the 90s.

    I can get behind this remake/retelling of the story as long as it stays true to being gothic level dark, ultra violent but also justified.

    5 votes
  7. Comment on The Crow (2024) | Official trailer in ~movies

    g33kphr33k
    Link Parent
    Thanks for that. I'll be grabbing it.

    Thanks for that. I'll be grabbing it.

  8. Comment on Looking to Llama. Help? in ~comp

    g33kphr33k
    Link Parent
    It is. So, my colleague has cracked using Tesseract to scan the videos and pull the clock cards. We have those. This bit is kind of niche, but if anyone wanted that code I'm sure he'd happily...

    It is.

    So, my colleague has cracked using Tesseract to scan the videos and pull the clock cards. We have those. This bit is kind of niche, but if anyone wanted that code I'm sure he'd happily share.

    MediaInfo grabs all of the data one could desire about the videos themselves. That's the json text file.

    Whisper is doing the caption VTT export for us, so that's done.

    Essentially, we now have data, we just don't know how to feed it to a LLM. YouTube has been a bit hit or miss, and the budget hasn't appeared to hire a pro/ML/AI data scientist/engineer. It's amazing the titles these people have when you go in that rabbit hole.

    I'm going to be spinning up Oobabooga to play with, but that leaves the training or RAG dilemma and how to.

    1 vote
  9. Comment on Looking to Llama. Help? in ~comp

    g33kphr33k
    Link Parent
    Let me break it down as this is a concept right now from an ask from the powers above. Example: We have 5 TV shows, multiple episodes of each, sitting and waiting for resale. A potential buyer may...

    Let me break it down as this is a concept right now from an ask from the powers above.

    Example: We have 5 TV shows, multiple episodes of each, sitting and waiting for resale.

    A potential buyer may query if we have a show of X name, or a show that is 60 minutes in length, or one that talks about cars.

    Using the media information outputted into json format (gives length, name of show, and lots of metadata) and the exported transcript of every single show, I want to feed this to AI to be able to then be queried as per the buyer perspective. It should then be able to answer the question.

    I have all of the information, but it's either a json or VTT caption file. Formatting them up to give to a model to ingest and spit back info from shouldn't be too difficult.

    That's really it. I'm doing this offline, I don't want to feed or pay for any third parties right now as it is all concept.

    Fun fact: I know very little about AI models outside of Generative AI for images using Stable Diffusion.

    1 vote
  10. Looking to Llama. Help?

    Hi folks I'm progressing a project but I could use some insights. I need to teach a LLM (preferably an open source and locally host-able) information about TV shows. I plan on using the show name,...

    Hi folks

    I'm progressing a project but I could use some insights.

    I need to teach a LLM (preferably an open source and locally host-able) information about TV shows. I plan on using the show name, title, running time, episode quantity per series/season, and full transcript.

    Where do I even start?

    Pointers to sites to learn to do this would be much appreciated. If anyone can summarise how I need to prep the data then that would be a bonus too.

    Bonus points for a Llama GUI that can be network hosted and allow different people to connect as individuals, a little like ChatGPT interface now.

    Thank you in advance.

    16 votes
  11. Comment on The Traitors - What a fun game show in ~tv

    g33kphr33k
    Link Parent
    Australia one has been cancelled. New Zealand version worth a watch, maybe? I have the Oz one to get through after the last 2 EPs of the UK to complete.

    Australia one has been cancelled. New Zealand version worth a watch, maybe?

    I have the Oz one to get through after the last 2 EPs of the UK to complete.

    1 vote
  12. The Traitors - What a fun game show

    I'm in the UK so I'm watching the version on the BBC, on iPlayer. Please, no spoilers as I'm only a couple of episodes into series 2. The concept is great. It's a really good crossover mix between...

    I'm in the UK so I'm watching the version on the BBC, on iPlayer. Please, no spoilers as I'm only a couple of episodes into series 2.

    The concept is great. It's a really good crossover mix between reality TV style of Big Brother (chatting about each other, making alliances), The Crystal Maze (group puzzle solving) and on top of that, it's playing detective.

    If you haven't seen it, I can highly recommend it. To anyone that has seen other international versions, are they better than the BBC version and worth a watch? I usually find US versions of things way too OTT. I refer to the styles of things like Kitchen Nightmares.

    14 votes
  13. Comment on OpenAI releases Sora: Creating video from text in ~tech

    g33kphr33k
    Link
    This is the first generation of text to video. RunwayML is giving you short clips but nothing compared to this. If this worries you already, give in 3-5 years of development and it'll be...

    This is the first generation of text to video. RunwayML is giving you short clips but nothing compared to this.

    If this worries you already, give in 3-5 years of development and it'll be terrifying. All the time OpenAI has resources for analysing huge quantities of exceptionally well meta-tagged data, their models will be leaps and bounds ahead of other companies.

    All this said, it's bloody amazing. Can you imagine how excited the marketing departments are? Why hire a film crew to make an ad when you can upload an image of the product and have AI generate the whole advert.

    18 votes
  14. Comment on OpenAI releases Sora: Creating video from text in ~tech

    g33kphr33k
    Link Parent
    Trump will eventually pass to darkness yet AI will keep him alive and his nutter followers will believe it is the second coming of the Messiah.

    Trump will eventually pass to darkness yet AI will keep him alive and his nutter followers will believe it is the second coming of the Messiah.

    4 votes
  15. Comment on Are any of you AI gurus? in ~comp

    g33kphr33k
    Link Parent
    Interesting. However, does this mean I'd have to convert the TBs of video before upload because that in itself is massively CPU/GPU intensive along with a lot more storage we're going to need. Oh...

    Interesting. However, does this mean I'd have to convert the TBs of video before upload because that in itself is massively CPU/GPU intensive along with a lot more storage we're going to need.

    Oh gees. That's the next thing to think about. Depending on the process to look at the video, does the AI have to have a specific format to process or will it read Master formats, which is typically AS-11. Else it'll get more complex daisy chaining a FFMpeg read and conversion and parsing it through the model.

    My brain is slowly churning this over. So much research required.

    1 vote
  16. Comment on Are any of you AI gurus? in ~comp

    g33kphr33k
    Link Parent
    I get that. However, it's all company IP and protected as much as possible. That said, half of it is on YouTube and a large portion of Legal's time is updating content ID for copyright or take...

    I get that. However, it's all company IP and protected as much as possible. That said, half of it is on YouTube and a large portion of Legal's time is updating content ID for copyright or take down. It's a losing battle (he says, as a massive pirate).

    I'm starting to think I could use a LLM for a large portion of this and link it to data from the TheTVDB. They have more accurate show data than we do. That would give us a headstart.

    2 votes
  17. Comment on Are any of you AI gurus? in ~comp

    g33kphr33k
    Link Parent
    Yes and pretty much. However, if we can get the data out to something sensible the latter part is easy enough to build as an old school DB. We could go as simple as PHP/Maria at that point with a...

    Yes and pretty much. However, if we can get the data out to something sensible the latter part is easy enough to build as an old school DB. We could go as simple as PHP/Maria at that point with a sprinkling of js.

    Getting the metadata is the fun part.

    1 vote
  18. Comment on Are any of you AI gurus? in ~comp

    g33kphr33k
    Link Parent
    How right you are. I work for a group of television production companies and we have a LOT of video from the past 30 years. As you guessed, we have master videos (broadcast) and we have a lot of...

    How right you are. I work for a group of television production companies and we have a LOT of video from the past 30 years.

    As you guessed, we have master videos (broadcast) and we have a lot of rushes (shot footage that may or may not have been in the show) which is often referred to as b-roll. That can be resold. We have footage of celebrities doing intimate and candid interviews along with concert and music events from bands that made it huge, but never aired. Having all of this indexed with meta data would be amazing but humans doing it would take real-time plus pausing and documenting. 30 years of shows which is tens of thousands of hours means we're past humans doing it and need to ask computers instead.

    5 votes
  19. Comment on Are any of you AI gurus? in ~comp

    g33kphr33k
    Link Parent
    Thank you for all of this. Lots to digest and research.

    Thank you for all of this. Lots to digest and research.

    1 vote
  20. Comment on Are any of you AI gurus? in ~comp

    g33kphr33k
    Link Parent
    I should probably have phrased it better. We know the people in our shows and they would be limited amounts. It would be great to be able to identify when they appear and what they say in each...

    I should probably have phrased it better. We know the people in our shows and they would be limited amounts. It would be great to be able to identify when they appear and what they say in each show. Maybe voice recognition would be more accurate and Whisper already does transcripts for us...

    This is why we're currently scoping the project.

    2 votes