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
Joined January 2011
Dmitri Pisarev retweeted
If your company needs software dev help, I’d love to talk to you! I have some amazing experienced US-based devs on the bench who are very good at using agents and have a high quality bar. We are best at mobile and web and desktop apps, but can do much more than that. Average experience level is 15 years. You’ll love working with them. Great people, excellent devs. Appreciate retweets and any referrals!
3
45
1
140
6,367
okay, despite some quirks, @t3dotcodes is probably the most usable universal agent orchestrator at this point. Codex is more polished, but I can't work without Opus.
1
2
178
wonderful. @conductor_build locked me out, makes me sign up for some reason, but sign up doesn't work. now I need to tell my t3code agents to recover my conductor chats.
3
2
226
okay signing in with chatgpt worked. none other method worked
58
Dmitri Pisarev retweeted
When I try to roll the windows down in my Roadster and I accidentally launch the car 60 feet into the air
114
2,107
113
36,510
824,175
geez I feel old. people are seriously asking such questions already
genuine question: why does every Windows PC start at the "C" drive? wtf happened to A and B?
1
88
vibed a synoptic gospel viewer on a canvas synoptic-canvas.vercel.app/ as a visual person, I always wanted to be able to see the texts of all 3 synoptics gospels together, trace the dependence, etc. now such things take less than ah hour, kinda sureal.
1
1
106
@jamonholmgren curious if you have been making any Bible study app experiements yourself or know nice examples of those who have. /cc @kentcdodds @Rasmic @gabegreenberg
1
37
How would a typical American use those $5K? My brain doesn't understand one-of sums at all. When invested, it's extra $30/mo. To my life it would make absolutely no measureable difference. (At the expence of $1.3T to the country)
Readers added context they thought people might want to know
Important context needed: Trump previously promised 2 dividends and never followed through. In early 2025, Trump publicly backed a roughly $5,000 “DOGE dividend” In November 2025, he promised a $2,000 “tariff dividend” newsweek.com/every-dividend…
58
Dmitri Pisarev retweeted
how it feels to get better at AI coding
23
129
16
2,366
70,468
Dmitri Pisarev retweeted
Open Al's internal benchmarks show GPT-6.1 Sol crushing Opus 5.5, with Anthropic struggling to keep up
413
1,005
846
16,500
7,902,171
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
3
148
the thing I like best about talking to LLMs
2
136
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
135
Dmitri Pisarev retweeted
Gemini has been slowing down AI development for nearly a year already.
370
897
290
19,194
1,499,279
dang it Astra low or med are so fast, given their intelligence levels (and feel even faster within the Codex app somehow)
1
2
119
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 😩
86
Finally iPhones can be a status symbol again for a while
1
48
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.
10
6
86
3,694
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’re 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
67