Figured I'd ask here because I have no doubt some of you are running some pretty cool, cost effective solutions for local models. Don't doubt some have mini data centers in their closets either haha, but just looking to get a view into what fellow HN'ers are using for their day to day work.
Unfortunately, I think many folks now just don't place any value on learning or knowing things because they can "just ask AI".
That's probably my biggest fear with AI is that people just don't see any value to knowing things anymore. And quite ironically, AI is amazing for learning new things.
I'd love to hear other takes on this though... Current thought is to just use something with a whole lot of exposure, in a whole lot of environments, pretty far downstream so the package hits all of that exposure, and hope someone spots it, kinda like xz. I tend to keep my base OS extremely minimal and do all my real work in VMs.
https://tolmo.com/blog/faster-than-anyone-can-fix-them/
What the PHP2Shell discoverer said on finding the issue:
> No special harness, or access to models that weren't generally available to everyone were used in the initial bug discovery. I focused on something I had a background in, knew its vulnerability history well, and held a theory that specific bugs lurk within the codebase. This shows that "know your target" is still as applicable as ever, even in the LLM dominated VR age. No model is simply capable of unearthing "all bugs" with simple prompts. At least for now.