• 1 Post
  • 21 Comments
Joined 11 months ago
cake
Cake day: June 4th, 2025

help-circle

  • Exactly this. My experience with our companies wrapper on Claude lines up with OP, not this comment thread.

    Everyone seems to forget everything you write is a liability. You can’t have bugs in code that is never written or generated, comments that don’t exist never become inaccurate, not duplicating “knowledge” into a repo doesnt have a risk of not aligning with business goals long term as they change.

    From what I’ve seen, people claiming a “10x increase” did not have a strong foundation to begin with and/or did not utilize tools like IDEs effectively. No offense to thread OP, which seems itself a generated response, but in the time he has done all of that a strong engineer would be long done. Everything listed should be done before ever getting into code along with business and product partners.






  • I currently run a mix of Ubuntu, fedora and bazzite machines at home and by far my favorite is bazzite. I may be a bit different as I work with containers, docker and k8s every day but it did take a little for it all to “click” for me. Once it did I’ve had no issues running anything with bazzite. On the other hand the number of hours I’ve spent chasing down issues on the Ubuntu machines due to dependency conflicts is embarrassing. Those issues simply do not happen with bazzite and the time I’ve spent learning the new mentality has been more enjoyable and significantly less than fixing problems on either distro. The atomicity and forcing isolation using containers is a paradigm shift, looking at is as workarounds, distro limits and Mcgyvering sort of misses the forest for the trees, but I get that its not for everyone



  • I’ve also been using bazzite with an nvidia card since the windows 10 death, my only callout would be VR is utterly broken for me. This isn’t a Bazzite problem, its due to nvidia drivers and impacts all Linux when using a wired headset (wireless is fine). I’m currently looking for a second cheap nvme to install windows to for just VR. If you have an AMD card everything works great. I’ve spent hours tinkering, switching to Monado and Xrizer from steamvr while tinkering with environment variables. Best I can do is get HL playable on 90hz with my index and a 3090. On windows I was doing 120hz pretty easily. Heres to hoping AMD really steps up next gen because I don’t want to support nvidia.











  • We do already know about model collapse though, genai is essentially eating its own training data. And we do know that you need a TON of data to do even one thing well. Even then it only does well on things strongly matching training data.

    Most people throwing around the word agents have no idea what they mean vs what the people building and promoting them mean. Agents have been around for decades, but what most are building is just using genai for natural language processing to call scripted python flows. The only way to make them look coherent reliably is to remove as much responsibility from the llm as possible. Multi agent systems are just compounding the errors. The current best practice for building agents is “don’t use a llm, if you do don’t build multiple”. We will never get beyond the current techniques essentially being seeded random generators, because that’s what they are intended to be.


  • It seems like you are implying that models will follow Moore’s law, but as someone working on “agents” I don’t see that happening. There is a limitation with how much can be encoded and still produce things that look like coherent responses. Where we would get reliable exponential amounts of training data is another issue. We may get “ai” but it isn’t going to be based on llms