Definitely agree. Most developers could build a basic Twitter or Facebook clone. The hard part is getting the users, content, and relationships that make the product worth coming back to.
It is both tbh. Anyone can build a poor clone of an application. However there are many things that you don't realise is happening beneath the scene.
It is all the small things e.g.
YouTube Mobile website works really well when you have a inconsistent connection compared to the alternatives such as Odysee, Rumble, Kick and Twitch.
I can listen to a live stream or a video style podcast in the car and YouTube will resume the connection properly as long as the browser tab on my phone hasn't gone to sleep. Kick will just stop, if it is a replay it will resume from the start of the stream after rewinding the stream a few seconds while attempting playback.
While the code to do this isn't that difficult. YouTube has bothered to deal with the edge case of someone like me driving through an area with inconsistent connection while running their mobile site (not even their app).
Whenever people try to use alternatives, they often complain about poor reliability of the app. A lot of the clones are losing users and I doubt they really even know they are doing it.
I've had it work well on both (iOS and Graphene OS) using Brave browser on both. It is simply much better when you are on a unstable connection than any of the other sites.
The main tradeoff I’ve found with running models like Qwen 3.8 locally is speed. On my hardware, they’re significantly slower than models served through OpenRouter, ChatGPT, or Claude.
That’s been fine for smaller tasks like analyzing a document, but for more involved work like refactoring code the latency makes it harder to iterate.
Yeah for live it's a bit on the slower side though still usable on the 4070 ti and 5080 our usual office desk has here, but I found it awesome running on background tasks rather than on demand, things like analyze this and that with this and that ruleset and applicable law warn me with source and justification for any error or missing part etc, qualify each returns with a ranking (certain with source, probable with reason, suggestion),... With its thinking mode enabled and it's great context size abilities it's really powerful, and each employee basically has their own assistant working in the background checking their files on its own as the day progresses
(the main reason is not just cost, it's data not going out and even mess leaving the EU, this essentially frees us of a lot of hurdles)
Yes, the generic system I built has unsloth/qwen3.8-27b with a 48000 context size running on each employee system with lmstudio, with a simple runner to watch folders and pass it to the llm alongside all context (our company design rules, our legal documents, our contractual rules, our applicable local law and reglementation, ...), return is then mailed to them or added to their personal dashboard event list, depending on their settings.
This is clearly pushing it memory wise and the gpu offloading is only partial but LM studio deal with it automatically and it's being fine even on the 4071 Ti desks (Ryzen 7500F and 32 GB of ram), employees get any feedback in ~20 minutes after they dropped a file (it's much smoother on the 5080 desks obivously), for live it's useless but as background helper it's great and the very large context allows us to fit all the rules we want in there.
One caveat has been to not ask it if everything is ok, but to find what's wrong - but always source and explain it and justify itself, never drown the user in warning in suggestions; goal is to help and provide a second pair of eyes not make them feel annoyed or unsecure.
And I found people to genuinely enjoy something that works for them on their own machine and is not tracked "by the boss", thus the assistant reference, than than a centralized mothership like we also have and they have access to. I also allow them to disable it if they want, I trust them with their work, but a second pair of eyes is always great.
(my previous workhorse for this was Qwen3-14b but it's missing a lot more edge cases)
reply