Just a guy doing stuff.

  • 2 Posts
  • 190 Comments
Joined 1 year ago
cake
Cake day: June 14th, 2023

help-circle
  • I’ve used a Z Fold 4 for two years now and it’s been the best phone I’ve ever had. Desktop versions of websites, on my phone, without feeling cramped. Two apps side by side, both roughly the size of a usual phone screen. Huge screen for retro emulation using a Bluetooth controller. All with still having a small screen for one handed use and more traditional scrolling.

    Games like Hearthstone, Gwent, Chess, Baldur’s Gate Enhanced Edition, Roller Coaster Tycoon Classic, feel way more playable.

    At this point, using any other device feels limited and cramped in ways that a big screen doesn’t.

    My only complaint has been price, and I only got mine because my company paid for it














  • Ah, I’ve generally run my VPN primary exit node in a public cloud infrastructure host like Digital Ocean or AWS in order to provide a separate public IP from the rest of my stuff, and not give out my home IP to public Wi-Fi and such.

    I like docker, as long as you use a good orchestration tool it’s a good way to declaratively define what should be running on your server, using a compose file or similar. There are a lot of benefits to the overhead of learning it, including running multiple instances of the same service on one machine without conflicts, and the ability to force your hosted apps to store all of their data in nice neat packages you can easily back up with something like Duplicity or Volumerize.

    I actually run my containers on a small kubernetes cluster using VMs running k3s atop Proxmox, with persistence handled by a hyperconverged ceph cluster. All probably very overkill but it’s fun to play with and performs incredibly. Most folks can get away with a single server running containers with simple docker compose.




  • You can dislike the statement all you want, but they literally do not have a way to know things. They provide a convincing illusion of knowledge through statistical likelihood of the next token occurring, but they have no internal mechanism for looking up information.

    They have no fact repositories to rely on.

    They do not possess the ability to know what is and is not correct.

    They cannot check documentation or verify that a function or library or API endpoint exists, even though they will confidently create calls to them.

    They are statistical models, calculating how likely the next token is based on transformations in a many-dimensional space in which the relationships between existing tokens are treated as vectors in a process for determining the next token.

    They have their uses, but relying on them for factual information (which includes knowledge of apis and libraries) is a bad idea. They are just as likely to provide realistic answers as they are to make up fake answers and present them as real.

    They are good for inspiration or a jumping off point, but should always be fact checked and validated.

    They’re fantastic at transforming data from one format to another, or extracting data from natural language written information. I’m even using one in a project to guess at filling in a form based on an incoming customer email.



  • Not the person you’re replying to, but my main hangup is that LLMs are just statistical models, they don’t know anything. As such, they very often hallucinate language features and libraries that don’t exist. They suggest functions that aren’t real and they are effectively always going to produce average code - And average code is horrible code.

    They can be useful for exploration and learning, sure. But lots of people are literally just copy-pasting code from LLMs - They just do it via an “accept copilot suggestion” button instead of actual copy paste.

    I used Copilot for months and I eventually stopped because I found that the vast majority of the time its suggestions are garbage, and I was constantly pausing while I typed to await the suggestions, which broke flow state and tired me out more then it ever helped.

    I’m still finding bugs it introduced months later. It’s great for unit tests, but that’s basically it in my case. I don’t let the AI write production code anymore