I am a Meat-Popsicle

  • 0 Posts
  • 695 Comments
Joined 1 year ago
cake
Cake day: June 10th, 2023

help-circle





  • Minimum open services is indeed best practice but be careful about making statements that the attack surface is relegated to open inbound ports.

    Even Enterprise gear gets hit every now and then with a vulnerability that’s able to bypass closed port blocking from the outside. Cisco had some nasty ones where you could DDOS a firewall to the point the rules engine would let things through. It’s rare but things like that do happen.

    You can also have vulnerabilities with clients/services inside your network. Somebody gets someone in your family to click on something or someone slips a mickey inside one of your container updates, all of a sudden you have a rat on the inside. Hell even baby monitors are a liability these days.

    I wish all the home hardware was better at zero trust. Keeping crap in isolation networks and setting up firewalls between your garden and your clients can either be prudent or overkill depending on your situation. Personally I think it’s best for stuff that touches the web to only be allowed a minimum amount of network access to internal devices. Keep that Plex server isolated from your document store if you can.










  • It tells me what document in the collection it used, But it doesn’t give me too much in the way of context or anything about the exact location in the document. It will usually give me some wording if I’m missing it and I can go to the document and search for that wording.

    I’m just one person searching a handful of documents so the sample size is pretty small for repeatability, so far, if it says it’s in there, it’s in there. It definitely misses things though, I’m still early in the process. I need to try some different models and perhaps clean up the data a little bit for some of the stuff.

    Using the documentation as source data It doesn’t seem to hallucinate or insist things are wrong, it’s more likely to say I don’t see any information about that when the data is clearly in the data set somewhere.

    YW on the responses I’m having fun with it even if it’s taking forever to get it to dial in and be truly useful.


  • Trident VGA?

    I got a 3DFX voodoo as soon as they came out. GL quake was mind-blowing.

    I bought a Riva TNT

    Then a GeForce 2

    Then a Radeon 9000

    Then for a bunch of years I just moved into laptop after laptop with discrete GPUs.

    Now I still have a 1080 and a 2070 doing a little bit of light AI work and video transcoding for me. But I’m still relying on crappy laptop GPUs for all my gaming. They’re good enough.


  • I have two projects for it right now. The first is shoving my labyrinth of HOA documents into it so I can answer quick questions about the HOA docs or at least find the right answer more effectively.

    The second is for work, I shoved a couple months of slack, some Google docs, some PDFs all about our production product. Next I’m going to start shoving some of GitHub in there. It would be kind of nice to have something that I could ask where is the shorting algorithm and how does it work and it could give me back where the source code is in any documentation related to it.

    The HOA docs I could feed into GPT, I’m out till you sleep apprehensive to handover all of her production code to a public AI though.

    I’ve got it running on a 2070 super and I’ve got another instance running on a fairly new ARC. It’s not fast, But it’s also not miserable. I’m running on the medium sized models I only have so much VRAM to deal with. It’s kind of like trying to read the output off a dot matrix printer.

    The natural language aspect is better than trying to shove it into a conventional search engine, say I don’t know what a particular function is called or some aspect or what the subcompany my HOA uses to review architectural requests. Especially for the work stuff when there’s so many different types of documents lying around. I still need to try some different models though my current model is a little dumb about context. I’m also having a little trouble with technical documentation that doesn’t have a lot of English fluff. It’s like I need it to digest a dictionary to go along with the documents.