2,487 karma · joined November 12, 2021
LI: https://bit.ly/48d9o9P
Email: yc@romanabashin.com
- 1
- "Guess too small"
- 9
- "Guess too small"
- 999
- "Guess too small"
- 9999
- "Guess too small"
- 99999
- "Guess too small"
- 999999
- "Guess too small"
- 9999999
- "Guess too small"
- 99999999
- "Guess too small"
- 999999999
- "Guess too small"
- 9999999999
- "Guess too small"
- 99999999999
- "Guess too small"
- 9999999999999999999999
- "Guess too small"
- 99999999999999999999999999999999
- "Guess too small"
- 99999999999999999999999999999999999999999999
- "Guess too small"
- 999999999999999999999999999999999999999999999999999
- "Guess too small"
- 99999999999999999999999999999999999999999999999999999999
- "Guess too small"
- 9999999999999999999999999999999999999999999999999999999999999
- "Guess too small"
- 999999999999999999999999999999999999999999999999999999999999999999
- "Guess too small"
- 99999999999999999999999999999999999999999999999999999999999999999999999
- "Guess too small"
Aww, fuck offIt was founder therapy first and foremost (and an exercise in serious play).
If you're into skeumorphism, you'll love it. I put a lot of care into how the buttons and other elements work and interact with each other.
(It's a free little dog journaling app I created with my partner to help us cope with losing our dog)
> BATTLE TANK © 2026 | Built with LEGO Style
What does that even mean?
Together with the out-of-the-box no effort AI slop design it's an immediate turn off.
(╯°□°)╯︵ ┻━┻
You only need to mention Protected Group Of The Week (I'm one of them and I like to research and read about history, so that makes it extra challenging) or anything resembling negative human emotions (guilty on that front as well), and the model screeches to a halt.
Just because OAI doesn't want another headline like "Chatbot convinces teen to off himself"
I understand this in principle, but I'm not convinced that dulling everyone's knives is better than figuring out how to keep them out of kids' hands
What are y'all comparing it with?
I’ve tried to find videos online but they all seem… normal?
I thought Germany was bad with no A/C and unopenable windows for "security" (= cost savings).
At least the busses* are on time.
* definitely not the trains, though
I've been to the Balkans, Central Asia, and rural Mexico for extended periods and they're all better than that (even if they might lack fancy digital screens, which is rapidly changing also).
Wtf, UK?
(I’m not from the UK, it sounds surprising.)
What would you say is the split of your token use (between main job / side project)? Do you use agents for everything?
I'm asking because I feel I'm weird in my usage, which is very much structured like 1. organising the context and then 2. send off requests to 1-2 models and continue down the rabbit hole from there. I've found agents take longer and make me learn/retain less about the system I'm building.
> At that price difference, lots of things that are viable to do in whatever harness the subscription allows are simply impractical via API, you'd be spending a whole developer's salary just for the benefit of using a different harness.
Could you elaborate on that?
Off topic: You did the ISBN visualization thing! Awesome!
I’m basically replicating myself multiple times for a ~10% salary surcharge.
In my mind it’s impossible to not see it that way, unless you just want to capture the subsidy surplus for free.
I don’t think everyone here is using Claude/GPT/… to create indie games?
If you’re using it for work then waiting another week/day/hour is a business expense, effectively.
Maybe it's like this guy I know who purchased a new-ish Bugatti but all the service is done by a local mechanic, during his time off, in a barn.
It’s more expensive, yes, but I assume most people here use it for something that is worth spending money on?