It's worth running, even quantized. I liked Meta Muse Glimmer's outputs, but qwen3.8-27b@q4_k_s kinda seems way better. Haiku/Sonnet kinda pairing in workflows?
It's easy to follow, it's a knee jerk tribalism reaction and not a logical or informed one. Go attracts backend or anti-frontend people so anything intermingling the two will draw out the commenters who bemoan anything that realistically builds a modern website. Just ignore it, your choice for dev tooling is practical and makes sense to me.
As someone who has had to clean up systems that only did a _npm install_ to get compromised, despite being good Renovate citizens, it doesn't matter if it is not "on the production path".
I don't care to hear arguments about how npm was _configured wrong_.
A tool with insecure defaults, with a long and storied history of being the vector by which data has been exfiltrated and companies hacked, needs to do an awful lot to justify still being used for any infrastructure our team is responsible for.
The proxy caches and package solution for Go has had its own drama.
My big contention with this project is that if I wanted to use node (or npm; or vite) in any capacity, I would have chosen node for that. I don’t want to use those tools in this context because it serves me worse than a well thought out solution.
The thought out solution is to isolate your frontend into its own directory. You can embed and serve that as part of your Go server. That frontend could have been done with react, vite, jsx, whatever typescript nonsense you want; without the Go parts necessarily needing npm or node in the build process.
Done. You have 2/3rds of Discord or Slack solved as just an insignificant fraction of my Private Cloud Project I just shared. Not interested in video or voice right now, it's easy to solve though. Also you'd have to solve for the mobile apps.
Edit: If you keep checking back, I'll have a video showing off that application. It's a bit beefy to just get up and running.
You go to person's profile. View their submissions. Use find via CTRL+F to seek out their "Show HN" submissions (or in this case, it's the top of the list because it's my last submission https://news.ycombinator.com/item?id=48970916 )
This is probably the first small model I got through some simple web game tests without having to reset the context. It tends to opt to overwrite an entire file instead of doing edits... which editing is where most of these small models fall apart along with getting stuck in repeating loops. Only 24k tokens in so far, it did some decent newbie work.
Tool calling at Q8 for this model is kinda impressive. It's doing patch edits like a champ. It gets stuck looping and doing the wrong things though as the context window grows.
Hi! This is a common issue regarding sampling parameters that are off. I imagine though that you are a smart cookie and read the model card, where it spoon feeds you the sampling parameters lol, so if it isn't this, could you please share more? I am one of the creators of this model :)
How much does it actually matter? I use to bother with these settings, but never really seems to fix the problems I commonly see. The issues I commonly see are small models getting stuck in a repeating loop, or they just fail at follow up calls for editing.
