Viewing profile — wilkystyle

This comment resonated with me so much, and it seems to be a minority view (at least on this website). I have found myself empowered by AI to tackle all sorts of things that would …

I was gonna say, you can dislike it because of the design, but understand that that's a subjective opinion that has nothing to do with whether AI is awesome. I actually like these …

Also, aren't instructions earlier in the prompt treated with more weight than those that occur much later? Sure, you could insert the system prompt later to avoid re-caching as muc…

> you can avoid installing the latest software — but that means you won't get any security updates, which are important They're not important if nothing can connect to the TV. > Or…

That is... quite a title.

Have they? https://www.cnbc.com/amp/2026/07/14/apple-prismml-ai-compres...

I also think something along these lines is the correct answer. It can be hard to pin down an exact metric because once you start optimizing for a metric it tends to not be a good …

Also, many of these sandboxing solutions provide features like network allowlists and credential masking/injection

Care to elaborate?

I'm so glad it's not just me. M1 MacBook Pro, here, and I quickly gave up on Zed because it felt so laggy to me. Thought it was something wrong with my MacBook (or maybe me).

What did you like about it?

Not the person you're replying to, and I have no idea what they were referring to, but I use agent-shell.el and it is incredible: https://github.com/xenodium/agent-shell xenodium i…

I had a similar thought to you, and found your question and the resulting discussion helpful!

Was already astounded that after decades of universally agreeing that number of lines of code is a terrible metric for software engineering productivity, devs are now using it as t…

I think you missed the point of the person you are replying to.

"Utah to hold Cloud providers liable for failing to police self-hosted VPNs on their infrastructure"

Not the person you are replying to, but I had the same thought come to mind. Every library and app seems to have its own way of disabling telemetry. In order for a unified way to a…

I have to imagine the takeaway from comments in this thread would be a big old "it depends." Which is the best almost certainly depends on what you are looking to optimize for and …

Curious to hear more. My experience is limited to llama.cpp on Apple silicon so far, but have been eyeing AMD ecosystem from afar.

I have personally found that I cannot context switch between thinking deeply about two separate problems and workstreams without a significant cognitive context-switching cost. If …

At least in e.g. Emacs and sublime text, you can mark all occurrences throughout the entire file. Assuming the matches are similar enough that the same motions apply even if you ca…

dot repeat is the wrong comparison. A closer one would be macros, but even then a good multiple cursors implementation is often faster, more intuitive, and requires less cognitive …

This assumes that the way things are now is the way things always will be. Right now AI is in its mainframe era (thin clients connecting to expensive compute somewhere else that yo…

but now you can build your AI agent toolkit to work on your init file for you