> that someone at Amazon merged for some reason

Yeah, the sensation is that the PR to a highly visible public repo did what it said it would on the box

If you're trying to get back into full-stack javascript or python engineering, you get to practice writing your own authentication layers and self-managing any dependencies you use for edge cases that don't make sense when you're normally working on backend.

It's great! crazy eyes all seriousness though, it's a terrible solution for the "vibe" space in terms of how careless people are about it. There are thousands of "who-knows-who-made-this" servers for major integrations out there.

This guy definitely has used WiX. What a nightmare!

This can be done with custom Modelfiles as well, I was pretty bent when I found out that 2048 was the default context length.

https://ollama.readthedocs.io/en/modelfile/

A Nokia candybar with one of those mall kiosk faceplates, Krylon Gold spraypaint the whole thing.

Welp, there goes my day.

Open WebUI can leverage the built in web server in LM Studio, just FYI in case you thought it was primarily a chat interface.

Cloudflare R3 might suit the scenario better for you in terms of the heavy assets, it's like AWS S3 except for the cool part where you aren't charged for data egress (last I checked! haha)

I'm about to buy Terraria after all these years, just so I can get the assets and check this out. You're cool :)

Oh Terraria is totally worth it, especially when spelunking with friends.

Its better than Minecraft, in my opinion.

R2

GitLab Duo got hit with an oopsie, "AI agent runs with same privilege to site content as the authenticated user" kinda oopsie where you could just exfiltrate private repo information via a pixel gif.

I knew it would get bad, but this bad already? I yearn for rigor haha

If you're working from OpenAPI, ideally you want to be able to process any, potentially full of shit formatting spec file. I find that half the integrations I run into have some old weird version of Swagger, and the rest work like hell to stay up to date with the 3.x spec track.

I agree, I wish, it will be a solved problem eventually. Just feeding a complex data model like that to the paper shredder that is the LLM, for making decisions about whether DELETE or POST is used is just asking for trouble.