Viewing profile — Greenpants

Alternatively, what I tend to do after receiving generated code is a lot of asking "why?". I've learned things I wouldn't otherwise have learned because I hadn't considered using t…

Agent-related files should've been dot-files at least to minimize human error. In fact, I'd been discussing: shouldn't agent instructions exist on a per-developer basis, and thus b…

The way I see it, it's the incessant stimuli you get through these apps. There's just no point where the screen stays quiet, stimulus free. Moving elements capture our attention na…

And those installed programs could have vulnerabilities that just a non-root user account could still take advantage of. Perhaps not likely for an LLM to do, but more so if you let…

Though I'm in the camp "people should really know to sandbox by now and be careful", I'd say we should also be mindful of how far from everyone has deep knowledge of the systems an…

I specifically chose a Mac Studio 128GB as my home server that's also running LLMs to be always online, in part due to the minimal idle power consumption and mostly fan-less operat…

Up to the point where consumers notice and decide to stop using these models because of it. Might be why we're already rarely seeing models output an "I don't know".

That's precisely why my agent use is IDE-agnostic: I run Pi in any terminal. Often use it with the terminal inside VSCodium, though sometimes in a terminal outside an IDE if I don'…

I'm afraid I'd have to agree. That is, unless you have 512GB+ RAM sitting on a shelf and run the much larger SOTA-comparable local models.

I'm glad you're asking. I already started writing a blog post on how to best make use of local models. I'll share it as soon as I have a complete enough list. If anyone else readin…

I get that it's a deal breaker to some; it definitely requires patience. In Pi, /new is my best friend and most-used command for sure. For simple tasks (I decompose complex ones an…

The other upside of running local LLMs is that there's no cloud provider to suddenly charge more for the same, or even less, model use. It's personal, but I prefer CapEx over OpEx …

Some of the work I do, I do for an (EU) organisation that doesn't have clear rules or guidelines on the use of AI yet. Though I have seen colleague-developers blatantly putting sou…

Let me put it like this. I started with local LLMs when ChatGPT still used GPT-3.5. I was amazed how my MacBook with 8GB RAM could run openhermes2.5-mistral: a 7b parameter model t…

I'm actually quite sure that directly retrying the tool call would often fix the edit-call already. But these models have been trained to "think" for a while for any problem solvin…

I have! I care about data privacy and LLMs being free. I'm using the Pi coding harness but containerized and sandboxed, to make sure it's running completely offline. On my Mac Stud…

I've dabbled a bit in GitHub Copilot using Claude Opus and Sonnet models via work, but I couldn't shake the thought that we weren't allowed to use this on any of our clients' codeb…

People choose the path of least resistance. If you can quickly swap out an old phone battery with one you can purchase in a store, it's as easy as doing groceries. If on the other …

https://blog.greenpants.net – my actively maintained blog where I write about my thoughts on AI given my Master's, share personal stories, tutorials and more. Lots of drafts coming…

The TODOs really help me get my logic sorted out first in pseudocode. Glad to inspire someone else with it! I've read that GPT-OSS:20b is still a very powerful model, I believe it …

I got a personal Mac Studio M4 Max with 128GB RAM for a silent, relatively power-efficient yet powerful home server. It runs Ollama + Open WebUI with GPT-OSS 120b as well as GLM4.5…

You might want to read "The Circle" if you haven't already. The reader gets to see an open-minded perspective of exactly this. Given your prior, I'd be curious what you think of it…