Agreed 😕 I hate short sessions with a passion. It's broken UX.
02.03.2026 10:29
👍 0
🔁 0
💬 0
📌 0
Agreed 😕 I hate short sessions with a passion. It's broken UX.
Session expiry is not fine. I don't care what auth you use, I don't want to have to spend the first damn half of my day awkwardly authenticating on a million websites.
Make your session last a year, it's fine, your site isn't a bank.
ICE IS THE BEST STATE OF WATER.
Asking my personal AI assistant to install a plugin which enables it to read my Google Calendar is just amazing.
Seriously, give it a try:
github.com/skorokithaki...
It's in a Postgres database on my server.
5/ I wrote an entire secure, featureful AI personal assistant, with long-term memory, a plugin system, the ability to make secure applications that run on it, audio/image/document capabilities, and a whole lot more, in just 3 days.
This kind of productivity would have been unthinkable last year.
4/ Another great benefit is that I know *exactly* how the whole system works, because I've built the entire architecture myself.
Sure, I don't know what the code inside the functions is, but it turns out LLMs are really good at that bit.
3/ The reviewer then reviews, and the developer goes back to work until there are no more review comments.
What I was pleasantly surprised to discover was that basically, past the plan stage, I didn't need to even look at the code. It all makes sense architecturally, works great, with minimal bugs.
2/ I thoroughly discuss and review the architecture with the architect until I'm satisfied that the approach is sound (here I have to make quite a few corrections usually), the architect writes a detailed (and moderately low-level) plan, and the developer goes to work.
1/ I've been working on Stavrobot (github.com/skorokithaki...) fervently over the past few days with a custom OpenCode architect/developer/reviewer/reviewer harness, and I am amazed at how fantastically few bugs I've seen.
Of course I had to make my own personal assistant agent:
github.com/skorokithaki...
It's more secure than OpenClaw, but perhaps not as competent yet. I really like it, though.
I couldn't wait to get my Pebble Index and made a pendant with a button that I can use to record my thoughts and notes. I also made an Android app that will receive, store, and transcribe those notes.
I'm really liking this, I'll write it up soon.
I really hate how I have to log in EVERY SINGLE DAY to the 100 sites I use, because someone opined that "long-running sessions are bad for security".
I ended up disabling 2FA everywhere because I couldn't deal with wasting 10 min a day logging in.
@owasp.org please update your guidance.
Claude today did something I've never seen before: it basically went "yeah man no idea" and asked if I want to talk about something it *did* know about.
Llama 3? Might as well get diagnosed by an abacus at this point.
The problem is that these studies will be obsolete by the time they're released, unless they go from inception to publication in a month.
After months of LLM-only programming, I wrote a program by hand again today. It was nice for a change, I think I'm going to do it again.
Ah, true. The caching layer is a great solution, I'm just really in love with Distill (to the point where I just elided tag pages altogether).
I recommend Django-distill, it generates HTML from the site and makes it completely static. That's how I generate Stavros.io.
Is GPT-5.2 Codex *way* too snarky for anyone else? It's been giving me lip for ages, and now it made a mistake and I got fed up at the snark and demanded it apologise.
This is its refusal.
The code in all my new projects is 200% written by an LLM. The trick is knowing which 100% to keep.
Fucking hell I can't believe what in reading. If your agent being "a little bit sensitive" means he murders an innocent woman, maybe no, he shouldn't be sensitive, or shouldn't be on the force.
Before I spend a bunch of time reinventing this wheel for the hundredth time, does anyone know of a simple 4x4, nice!nano/ProMicro-based macropad PCB?
If not, do you want one to exist?
I made another little bedside clock, and I love it:
www.stavros.io/posts/i-made...
If you're interested in making things/3D printing/circuits/software/whatever, our making community has a low-volume newsletter you can sign up for:
www.themakery.cc
Exactly, all that's happening now is people is finally learning a (very late) lesson.
I can't decide if the fact that a post about archiving is unavailable is ironic or exactly the point.
@profanity.accountant do me!
I don't understand how Google can be smart enough to create the world's most powerful LLM, but not smart enough to make an LLM web app that doesn't lose your message when you navigate away for a second.
Seriously, what's going on?
I don't know about most bribable head of state, but there's definitely no more *openly* bribable head of state.
This looks fantastic.