The other day I was bouncing ideas back and forth with an LLM, when I realized the effort was at high, and the model was honestly quite powerful. That whole brainstorming session didn't need to tap into frontier intelligence to crunch some numbers like a regular calculator could, and help me navigate new concepts, in fact a decent 8B would have handled the whole thing just as I had needed anyways. YET I was using the literal frontier of human technology to do everyday stuff. Running LLMs locally has always had some friction to it, GPT sits there in the browser, Claude, Deepseek, all of em are super accessible. That's definitely easier than installing a runtime and pick between things that require thoughts and process, just to get a model that is noticeably worse at tasks. In my X timeline I'm really starting to see those quants becoming something people, devs and labs are running everyday locally, on their own hardware in alternative to them anthropics and GPTs. Small models got a lot better over the past year, and they are starting to run on laptops and smaller devices. The setup is still A LITTLE annoying, which I think is the real reason most people never tried again after the first bad experience.
So I m curious where everyone actually lands on this (what's the general consensus looking like);
If running a capable model on your own machine took one click and cost you nothing, would you move your everyday tasks over? Or is there something about them GPTs and Anthropics you d keep going back for?
Anyone here building something around sustainability? I ve been browsing for a while and haven t seen many products tackling climate change or other global challenges.
A real situation from freelance work: a project was delivered and approved, and then the client sends a change every few days. Each one takes 15 minutes, so saying no feels petty. After a month it is several hours of unpaid work and the client has stopped treating it as extra.
The options I know: a fixed number of free changes in the contract, a small monthly support plan, batching requests into one weekly list, or just charging every time. Each has a cost, and the first one only works if it is agreed before the project starts.
Why is the "Use data for AI training" toggle ON by DEFAULT? I have noticed this on LinkedIn and Instagram, where this feature is ON since I don't know when, and additionally is also hidden away in a chinese box-esque nested settings? I enjoy using AI when it's used in the RIGHT ways, to help humans in ease of life without taking away their freedom or privacy. I'm pretty sure these major companies never asked me for permission to introduce AI into their platform and use my data, and it's pretty disturbing how blatant they have become about it. If people have noticed other such applications, please let me know in the comments so I can turn it off.
I thought feeding the entire repo to the agent would make it smarter. Instead, it starts getting distracted by legacy code and tries to "clean up" stuff completely unrelated to my prompt.
you literally ask for a button color change and it delivers a pull request touching twelve different files.
How do you guys restrict the working directory or keep the agent focused on just one file?
I've been automating social posts for a small business with n8n and Zernio, and the generating and scheduling part works great. The part I keep getting stuck on is the approval.
The client has to say yes before anything goes live, and right now that means sending screenshots on WhatsApp, waiting, and then going back to the flow by hand. And when something goes out wrong, there's no clear record of what they actually approved.
I ve used the same task manager for almost three years. It works fine, but every time a new launch shows up here with a cleaner design or smarter features, I wonder if I m just stuck in a habit.
Last month I tried switching to a newer app for a week. It looked better, but I spent more time moving my tasks and learning shortcuts than actually getting things done, so I went back to my old one.
It made me wonder if loyalty to an old tool is a smart choice or just a fear of the switching cost.
How do you decide when a tool has stopped serving you and it s worth the effort to switch? Has switching ever paid off for you, or did you regret it?
