richstokes

Device-bound would be a nightmare. I don’t want to have to think about different credential for phone vs. laptop, etc.

I got steamos working on my nvidia PC with a bit of messing about. I really like it, it’s a fun experience and after this initial hack, everything has worked great.

https://github.com/richstokes/SteamOS-Nvidia-Drivers

Is it a nightmare? I pasted the first, zoomed out, image of the shirt into ChatGPT, and it decoded it / let me know what the bash script does in one shot

Pretty bad. It seems to have very limited context, and it mostly cant follow up on things if you have additional things to ask. It was ~fine when it first came out, but seems to have made basically zero progress since then, and frankly feels pretty dumb compared to talking with modern LLM-type apps.

American football is unwatchable to me for that reason. It’s so stop-start. 30 seconds of play followed by 3 mins of ads. It’s just insane. Feels like the entire game was designed around maximizing commercial sales heh

Andddd now everyone knows that an arbitrary text string in a device hostname is enough to ground a flight.

What if you deploy to a different CPU architecture than you develop with? Some languages/libraries use pre-compiled binaries as part of their packages.

I wonder if you could repurpose the cars SIM card (eSIM or otherwise) / cellular modem for your own use? Like presumably the manufacturer is paying a data plan to a cell provider. If the connection is not locked down to specific traffic I wonder if it could be reused

It was the Wild West back then. Good times!

Kinda related but I used to practice guitar in my dreams. If I had been learning something I’d often dream about playing it over and over again, and even going beyond that and figuring out “solos” and melodies and stuff over the chord. Can’t be sure if it translated into any real life skill, but it felt like I was actually learning or at least strongly reinforcing what I’d been practicing.

Was thinking the same honestly. GH is very sticky though, especially when you have actions and all kinds of other integrations set up. But it’s just kind of absurd at this point how many outages they have.

Are there benchmarks of this / what’s the best way to compare it against paid models? With all the rate limiting in Claude/Copilot/etc, running locally is more and more appealing.

Do you use it with ollama? Or something else?

My personal Claude sub (Pro), I can burn through my limit in a couple of hours when using Opus. It's borderline unusable unless you're willing to pay for extended usage or artificially slow yourself down.

The problem is half the time you don't know you need the better model until the lesser model has made a massive mess. Then you have to do it again on the good model, wasting money. The "auto" modes don't seem to do a good job at picking a model IME.

Agreed. What network are they forgetting here? Pretty sure I've only ever seen that apply to wifi. Are they trying to say you might need to re-pair a bluetooth speaker on a date? I don't get it.

Probably not. That would slow them down. The turbo button under-clocked CPUs :-)

“Like carfax but for your home” is a really interesting idea. So many homes are bought with little-to-no history beyond an inspection of questionable thoroughness.

If this became the norm, somehow, it would be a really helpful tool for both buyers and sellers.

Easily one of the top 25 horse drawing sites of 2026

Same. I’ve had good results with read only accounts / tokens and let the agent have at it. Also works with terraform, aws cli, etc.

One does not need a new/separate tool to do any of this, just include it in your agents instructions.

This. It's a false economy if you value your time even slightly, pay for the extra tokens and use the premium models.

I think it's configurable, but my experience with terraform is that by default when you `terraform apply` it refreshes state, which seems to be tantamount to running a new plan. i.e. its not simply executing whats in the plan, its effectively running a fresh plan and using that. The plan is more like a preview.

Why?

Is there a way to use this on models downloaded locally with ollama?

It garbles up the formatting when importing / exporting. You can’t collaborate with people on office in a meaningful way.

I recently discovered you can use uv to run code direct from a git repo.

No need to clone/manually install packages first. E.g. `uvx --from "git+https://github.com/richstokes/meshtastic_terminal.git" meshtastic-tui`

It’s like a crap Linux theme pretending to be windows vista or something. I don’t get it.