Sign in

Stavros

@stavros.io
351 followers 21 following 273 posts

I like making things. Most of them are silly. Sometimes I post about them.

PostsRepliesMedia
Stavros @stavros.io · 27/09/2026
I couldn't find a travel planner I liked, so I made one: www.wherewhen.cc Invite only for now, but here are some: KGHW-3GA8-6VUQ YC9B-23HT-7K4F 3TZ7-ZFM7-TUPP 6NMQ-JHBE-7JNY 49T5-M8N7-W7MW Feedback appreciated! Keep in mind it's under rapid development, but your data is safe.
wherewhen.cc
Wherewhen
Where next? When you’re ready.
000
Stavros @stavros.io · 25/09/2026
Yeah I implemented it as that now.
030
Stavros @stavros.io · 21/09/2026
I got a Pebble Index ring, and I made it so if I say "mayday" to the ring, my phone rings with a fake incoming call. Thanks @ericmigi.com for getting me out of awkward social situations.
2285
Stavros @stavros.io · 18/09/2026
@ericmigi.com are there any plans to make an Index app for the Pebble, that lets me record notes with the watch (as if I was recording them with the ring), for the times my ring isn't with me?
010
Stavros @stavros.io · 12/09/2026
It's supposed to last two years, but knowing that every use takes it closer to the end is stressful.
010
Stavros @stavros.io · 04/09/2026
Wait, what's GPT-5-astra?
010
Stavros @stavros.io · 03/09/2026
It's a silly psychological hangup, but it's really limiting my use of it. Whenever I have a thought, I figure "well my phone is in my pocket, I'll take it out and record it there and save the ring". If there were a rechargeable version, if definitely get that instead, just to not have this fear.
110
Stavros @stavros.io · 03/09/2026
1/2 I bought a Pebble Index 01, a ring for recording voice notes, by @ericmigi.com. I really like it, the app is great, and the team is very responsive. There's one big issue, though: Because it's not rechargeable, I find myself not using it because I don't want to spend the charge.
200
Stavros @stavros.io · 06/08/2026
Oh hi VB3!
010
Stavros @stavros.io · 02/08/2026
I have a small projector that is sitting idle, and I was figured I'd have it project something on the bedroom ceiling. Here's an aurora with an accurate starfield over your current location: skorokithakis.github.io/ceiling-auro...
skorokithakis.github.io
Ceiling Viz
000
Stavros @stavros.io · 31/07/2026
I'm confused about this, don't you authenticate satellite images somehow? How does that work, does someone send a satellite image showing something and it gets treated as valid evidence? I'd expect that the images came from verified sources, not random Internet Joes?
000
Stavros @stavros.io · 12/07/2026
@ericmigi.com Is there any update on the Index 01? Back in May most were supposed to have been shipped by now, but we haven't heard anything.
000
Stavros @stavros.io · 12/07/2026
I think Ryan has a point, "either on device or in Meta's cloud" is a false dichotomy. It could be on your own computer at home, it could be a cloud you trust, it could be *something*. Those aren't the only two choices.
100
Stavros @stavros.io · 06/07/2026
This is amazing.
000
Stavros @stavros.io · 05/07/2026
Let me know if you ever need a Greek.
020
Stavros @stavros.io · 27/06/2026
No, this was before you paid anything. Nowadays you get the annoying loss of functionality *after* you pay.
010
Stavros @stavros.io · 27/06/2026
I need the Rated Xmas one.
010
Stavros @stavros.io · 21/06/2026
I... don't think it's new.
020
Stavros @stavros.io · 20/06/2026
That sounds like he's doing a bit, though.
010
Stavros @stavros.io · 16/06/2026
Plugged ear, huh? I get that a lot too, small ear canal.
010
Reposted by Stavros
Micah @rincewind.run · 12/06/2026
a little on the nose for capitalism that the world’s first trillionaire is a nazi conman
4898842572
Stavros @stavros.io · 11/06/2026
It used to be that one engineer wrote the code, another reviewed it. Now the first engineer uses Claude to write the code, and the second engineer uses Claude to review it, and then everyone complains that engineers might be out of a job soon.
021
Stavros @stavros.io · 10/06/2026
PSA: Water is not transparent. Water is actually *very slightly* blue.
010
Stavros @stavros.io · 03/06/2026
Hey now, we can't be saving the lives of random people! That's chaos.
020
Stavros @stavros.io · 03/06/2026
Hey @martin.kleppmann.com, I saw you tried www.writelucid.cc, I got an error that the API key is out of credits, I don't know if that surfaced in the UI properly. You should get a better error message now, if you want to try again.
writelucid.cc
Lucid, write in your voice with AI critique
Lucid is an AI editor for long-form writing. It reads your draft and leaves margin comments on your sentences. It never rewrites your prose. Try it now.
010
Stavros @stavros.io · 02/06/2026
Google still does not understand that I might want to join a meeting without giving work access to my entire personal phone.
010
Stavros @stavros.io · 01/06/2026
Well, if Claude is better than the average parent at parenting, I'm glad parents are talking to Claude.
120
Stavros @stavros.io · 01/06/2026
My god the articles feel like they're all written by Claude. All the Claude writing really grates on me. It's as if I'm reading articles written by my dad all day. Sure, he's a decent writer, but I don't want to *only* read his stuff, plus if I wanted something, I'd just ask him.
141
Stavros @stavros.io · 31/05/2026
www.writelucid.cc
writelucid.cc
Lucid, write in your voice with AI critique
Lucid is an AI editor for long-form writing. It reads your draft and leaves margin comments on your sentences. It never rewrites your prose. Try it now.
030
Stavros @stavros.io · 25/05/2026
I have no sense of the set to know whether it's underrepresented or not in it, it's versions of 90s shareware. No idea if that's rare or common.
020
Stavros @stavros.io · 24/05/2026
I have a bunch of old software from the 90s and 00s sitting on my NAS, should I upload them somewhere?
110
Stavros @stavros.io · 24/05/2026
The problem with LLMs is that they're accessible, so everyone thinks they're an expert on them. It's like swinging a hammer around and then complaining the hammer ruined your house. Let alone the "omg LLMs have massive environmental impact because we're all using them all day long!".
010
Stavros @stavros.io · 24/05/2026
2026.
000
Stavros @stavros.io · 17/05/2026
I don't understand this pushback, if I'm citing something, doesn't mean I'm referring the reader there for more info, or basing my paper on a claim the cited paper made? I don't understand in which situation one would cite a paper they couldn't read, or verify the accuracy of.
020
Stavros @stavros.io · 12/05/2026
I made a little utility that lets you use Linear as your OpenCode frontend (working on multiple items at once): github.com/skorokithaki...
github.com
GitHub - skorokithakis/symphony: An implementation of OpenAI's symphony with OpenCode and Linear.
An implementation of OpenAI's symphony with OpenCode and Linear. - skorokithakis/symphony
020
Stavros @stavros.io · 05/05/2026
I wrote a quick script to calculate how many times the AI architect/reviewer rejected an implementation per implementor model. Basically an AI change failure rate. @simonwillison.net do you know of anything else like this? Could be an interesting aggregate metric.
000
Stavros @stavros.io · 05/05/2026
Sonnet is FIFTY TIMES more expensive than DeepseekV4 for lower quality! Amazing, just unbelievable.
001
Stavros @stavros.io · 05/05/2026
I compared implementor LLMs: * GLM-5.1: a bit sloppy. It did deliver the feature. $3/mo plan. * Qwen3.6: ran out after $5. OpenRouter didn't use cache. * DeepseekV4: made 2/4 of the same mistakes GLM-5.1 did but way more thorough. $0.09 via DS API. * Sonnet: sloppiest. Works, half-assed.
100
Stavros @stavros.io · 04/05/2026
I wanted to be able to get AI to improve my writing without losing my own voice, so I made an app for it: www.writelucid.cc
writelucid.cc
Lucid
Write in your voice, with AI critique.
041
Stavros @stavros.io · 03/05/2026
I wrote a new article! Adding a feature to a closed-source app using LLMs: www.stavros.io/posts/adding...
stavros.io
Adding a feature to a closed-source app - Stavros' Stuff
021
Stavros @stavros.io · 01/05/2026
Do tell!
100
Stavros @stavros.io · 28/04/2026
No, absolutely, taking feedback and growing is not a prerequisite for being able to comment online. You can definitely just keep spouting uninformed bullshit. Enjoy your day!
100
Stavros @stavros.io · 28/04/2026
Here's an interesting rebuttal: mvaleadvocate.substack.com/p/the-abstra...
mvaleadvocate.substack.com
This Guy Says AI Can Never Be Conscious. Here's Why He's Wrong.
On Alexander Lerchner’s paper, and why a chemistry textbook would have saved everyone a lot of time.
000
Stavros @stavros.io · 28/04/2026
That's a good reference, thank you.
010
Stavros @stavros.io · 28/04/2026
I know how they work. You need to understand that "they're just X, therefore they cannot do Y" is not a convincing argument by itself.
110
Stavros @stavros.io · 28/04/2026
You can't just handwave the proof with "just look at it!" and also wonder "how can people not understand this". You need to show that, for example, LLMs can't make up their own language.
100
Stavros @stavros.io · 28/04/2026
OK, and how does that lead to "therefore they cannot create their own unique thoughts"? Without concrete, logical steps in the middle, I could just as easily say "humans cannot form their own, unique thoughts, they're a bunch of cells stuck together".
230
Stavros @stavros.io · 28/04/2026
Interesting, do you have any research or evidence that shows this? That would help them understand.
100
Stavros @stavros.io · 27/04/2026
I'm watching Euphoria and it struck me that it's all about body positivity and acceptance for women but men are divided into big and small dicks.
010
Stavros @stavros.io · 24/04/2026
I made a small tool for your LLM to manage intangible knowledge on your repos quickly and easily: github.com/skorokithaki... It notes stuff that's not in the code, such as the options you *didn't* choose.
github.com
GitHub - skorokithakis/gnosis: A knowledge base for what the code can't tell you.
A knowledge base for what the code can't tell you. - skorokithakis/gnosis
000