Viewing profile — josefcub

You know, I took this when there were only a handful of people on the leaderboard. Things I didn't know: 20-40 minutes is 2 hours if you're like me and want to make sure you're act…

Nah, it's really a question of complexity regarding the sheer amount of hardware that needs supported. Apple tightly controls what hardware they write Mac OS for; this lets them ma…

I would recommend against this. Check your local and EU laws -- Anything coming out of your IP address may end up being your responsibility if it turns out to be illegal. Another t…

Well, I ran a couple of experiments a couple years ago against a 10.7b SOLAR-based language model and MUDs. What I found is that dumping one into a MUD that had been built specific…

I've never used such a thing. If the intent is to get the LLM to not perform reasoning before it answers, most of the APIs have a toggle that lets you minimize or stop thinking. I'…

Hermes Agent is really decent. Don't rethink your entire company, offer your customers choice instead. Some may prefer OpenClaw and others might be better served with Hermes Agent …

I'd started using DOS-based machines in the 80s, and ended up with a copy of WordStar 3.3. I used it so much as a kid that I still have the WordStar keybindings stuck in my muscle …

Brave's "Leo" AI is configurable enough to specify local endpoints for processing, instead of going wherever they want it to go. I've set it up to use my own systems, and it works …

I've got 256GB of RAM on a Mac Studio M3 Ultra. Other posters are right: The M3 Ultra's prefill is super slow with really large models, 3-5 minutes while it digests the new additio…

My google-fu is failing me at the moment to cite sources, but here's an example ~/.config/crush/crush.json file (based on my own) showing the options to remove telemetry and provid…

Try charmbracelet's crush, found here: https://github.com/charmbracelet/crush Crush is pretty new, but getting better all the time. It's written in Go, so no node hijinks to get it…

I am! I moved from a shoebox Linux workstation with 32MB of RAM and a 12GB RTX 3060 to a 256GB M3 Ultra, mainly for unified memory. I've only had it a couple of months, but so far …

I think this is fun! I ended up with 92/102, because a few were non-obvious. If I had a critique it's that the AI entries were repeated on multiple occasions, making the decision b…

I'd listen to that on the radio! LOL 2.3L 4-cylinder. Good enough for the light truck tasks I usually end up having. It's the last year of the first generation Rangers. I had a 198…

I'm going to buck trends and get my hands dirty -- The oil needs changed and the O2 sensor needs replaced on an old (1992) Ford Ranger pickup truck I recently acquired. Bought it f…