I believe in Christ. Also I'm a web developer who's learning design thinking. ex-@neoscms team member. #reactjs all things! In love with #opensource

WFH
Not many people are gifted enough to be paid for doing mathmatics, sports, or being an actor. Programming is turning into one of those kind of activities.
1
2
93
the thing I like best about talking to LLMs
2
89
let's build an LLM on top of jev lol
"jev can't generate text" But jev has a lot to say! I gave him a couple hundred common english words to choose from + punctuation
101
Dmitri Pisarev retweeted
Gemini has been slowing down AI development for nearly a year already.
374
905
19,304
1,494,703
dang it Astra low or med are so fast, given their intelligence levels (and feel even faster within the Codex app somehow)
1
2
112
There's that thing called responsive design... Since 2012 I've learned to develop for the full range of screen sizes, rather than optimising for some.
Me as a developer seeing the new iPhone duo 馃槱
82
Finally iPhones can be a status symbol again for a while
1
47
Dmitri Pisarev retweeted
You'll know when AI gets de novo reasoning ('AGI'), because it won't look anything like 10,000 monkeys exploring 991,235 dead ends before finding the correct path.
11
6
87
3,620
Crazy is that AI is gonna solve humanitie's most intellectually challenging problems before it's able to use useEffect properly or roll basic abstractions in a sane way
We鈥檙e sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics. The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra. The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.
1
2
66
it's remarkable how main brain just filters out all of these amazing 3D slop-demos my timeline is full of. like, it's trained to detect human effort, all of the one-shotted things don't interest me at all.
2
2
86
*my brain. I'm cheap and I ain't paying for Premium twttr lol.
21
I have a very precise way to predict way the new frontieer models are going to ship: Just last week, my view of Sol/Fable changed from "omg they are so taking my job" to "this piece of shit can't get anything right", and that's how I knew new models are around the corner.
1
3
91
half the twtr sucking up and the other half hating on that one rich guy is pretty funny.
53
Somehow Twttr resets me to "For you" tab once in a while, and I only notice when my cortisol levels go through the roof. I'm so afraid of stupidity.
2
96
ahahah love this sort of humour
Them: Billionaires should do more for society!! Billionaires: Okay, here's $10m for a Linux nonprofit to make the prophecy of desktop liberation come true! Them: NO, NOT LIKE THAT!!! 馃槨馃槨馃槨 oligarchy.fyi/
1
153
Expectations: agents do our work, we relax and enjoy life Reality: I sit all day de-sloppifying and taking responsiblity over 50KLOC PRs.
4
92
How my morning started: a colleague asked for a review...
1
84
the agents are absolutely blind in terms of distingushing good vs bad abstractions. 90% of my feedback to the agents is about abstraction style. I feel like Yoda master.
2
87
Dmitri Pisarev retweeted
Idea guy evolution Before: 100 abandoned ideas After: 100 abandoned apps
1
4
79
gosh Opus 5 is kinda trash. I feel still relevant as a developer when Sol/Fable leave the room.
1
2
129