The other year I came to the same conclusion so I built a web frontend for yt-dlp with queue support. I have 'profiles' that I can pick from at the time of download that allow custom yt-dlp configs to be active at any given time, which routes videos to different locations and jellyfin being one of those locations.
I've had the opposite experience. Spec driven development really makes things much easier to maintain. If you're just yolo'ing it and throwing prompts around things will fall apart fast.
People have nothing in common with tech giants. Tech giants support whoever is in power, because money. The current tech giants kicked the current President off of their platforms back in the day. Now these tech giants hang out at the White House. Funny how that works.
I have a 48GB M5. I don't need to run larger models. I want more context. I've managed to set the context window at 71,680 using Qwen3.8-27B-oQ4e-fp16-mtp. But I want more. Is anybody, with similar specs, able to set their context window higher?