Pumpkin Escobar

Yeah. Zen is a bit newer and I’d say not quite as slick an experience yet, but it has come a long way in the last couple months and is getting very good

Firefox-based https://zen-browser.app/ if you want to get fancy

Or the world blows up and it’s all over. I guess what I’m saying is, no downside, fire it up and let’s see what happens.

Cruel and unusual.

Also, reporting that Trump Tower (either) should be renamed Mexico Tower feels pretty good.

You understand, he… does not

Yeah yeah yeah… yeah

no fact checking and a ton of bots being added? Sounds like a fantastic place to spend time. /s

I have some Zooz relays and can also recommend. There are also two options, you can either get the zooz switches which replace your current switches ( https://www.thesmartesthouse.com/collections/light-switches/products/zooz-800-series-z-wave-long-range-wall-remote-zen37-800lr-battery-powered?variant=40387548938303 ) or the relays ( https://www.thesmartesthouse.com/collections/z-wave-relays/products/zooz-700-series-z-wave-plus-dry-contact-relay-zen51 ) that you install in the box behind your existing switches.

Our house has some fancy switches downstairs so I went with the relays for the few switches I wanted to automate. One thing to note, it’s not always easy to fit the relays in the box, if there’s a lot of spare wires in the box, it can be sort of cramped.

Ollama and openwebui for a nice web interface.

DNFTA

First a caveat/warning - you’ll need a beefy GPU to run larger models, there are some smaller models that perform pretty well.

Adding a medium amount of extra information for you or anyone else that might want to get into running models locally

Tools

• Ollama - great app for downloading/managing/running models locally
• OpenWebUI - A web app that provides a UI like the ChatGPT web app, but can use local models
• continue.dev - A VS Code extension that can use ollama to give a github copilot-like AI assistant running against a local model (can also connect to Anthropic Claude, etc…)

Models

If you look at https://ollama.com/library?sort=featured you can see models

Model size is measured by parameter count. Generally higher parameter models are better (more “smart”, more accurate) but it’s very challenging/slow to run anything over 25b parameters on consumer GPUs. I tend to find 8-13b parameter models are a sort of sweet spot, the 1-4b parameter models are meant more for really low power devices, they’ll give you OK results for simple requests and summarizing, but they’re not going to wow you.

If you look at the ‘tags’ for the models listed below, you’ll see things like 8b-instruct-q8_0 or 8b-instruct-q4_0. The q part refers to quantization, or shrinking/compressing a model and the number after that is roughly how aggressively it was compressed. Note the size of each tag and how the size reduces as the quantization gets more aggressive (smaller numbers). You can roughly think of this size number as “how much video ram do I need to run this model”. For me, I try to aim for q8 models, fp16 if they can run in my GPU. I wouldn’t try to use anything below q4 quantization, there seems to be a lot of quality loss below q4. Models can run partially or even fully on a CPU but that’s much slower. Ollama doesn’t yet support these new NPUs found in new laptops/processors, but work is happening there.

• Llama 3.1 - The 8b instruct model is pretty good, decent speed and good quality. This is a good “default” model to use
• Llama 3.2 - This model was just released yesterday. I’m only seeing the 1b and 3b models right now. They’ve changed the 8b model to 11b, I’m assuming the 11b model is going to be my new goto when it’s available.
• Deepseek Coder v2 - A great coding assistant model
• Command-r - This is a more niche model, mainly useful for RAG. It’s only available in a 35b parameter model, so not all that feasible to run locally
• Mistral small - A really good model, in the ballpark of Llama. I haven’t had quite as much luck with this as with Llama but it is good and I just saw that a new version was released 8 days ago, will need to check it out again

It’s a good thing that real open source models are getting good enough to compete with or exceed OpenAI.

I’ll preface by saying I think LLMs are useful and in the next couple years there will be some interesting new uses and existing ones getting streamlined…

But they’re just next word predictors. The best you could say about intelligence is that they have an impressive ability to encode knowledge in a pretty efficient way (the storage density, not the execution of the LLM), but there’s no logic or reasoning in their execution or interaction with them. It’s one of the reasons they’re so terrible at math.

I like the game, but agree with the over-tutorialed complaints. They have two difficulty modes, I wish only story mode got all the handholding. I think there’s enough obvious indicators to get you through all the game mechanics.

It has been on my list to figure out how to move to forgejo, need to do it soon before the migration process breaks or gets awful.

Donnie Darko - Just such a great, strange movie

Shoot your shot, player.

Don’t go crazy or over the top, don’t overdo it, but just say it. If they’re a good friend they won’t be scared away. If they’re like you that way you’ll both be happier.

Don’t overthink it, ask them if they’d ever like to hang out or do something more like a date.

Ballsy, direct, badass. That can be you.

Dating is awkward but life gets a lot better once you get more comfortable with it. Everyone is a dating idiot until they’re not, there’s a good chance your friend is still in the idiot stage and maybe hell be over the moon that you helped push through it.

I’m a Unity noob and even more of a noob in Godot, but the c# development experience is so much better in Godot it’s ridiculous.

I remember what was it like 6 years ago when Unity announced moving towards .net core. I can appreciate thats a large effort, but they’ve made ridiculously little progress that I can see

Taking ollama for instance, either the whole model runs in vram and compute is done on the gpu, or it runs in system ram and compute is done on the cpu. Running models on CPU is horribly slow. You won’t want to do it for large models

LM studio and others allow you to run part of the model on GPU and part on CPU, splitting memory requirements but still pretty slow.

Even the smaller 7B parameter models run pretty slow in CPU and the huge models are orders of magnitude slower

So technically more system ram will let you run some larger models but you will quickly figure out you just don’t want to do it.