Building with agents

PNW, Canada
Joined May 2025
One of my own pet-peeves in a workplace is having more than one boss. If two people are trying to direct my actions and I don't have the authority to resolve conflicts then it leads to frustration and demotivation. This is a scenario that multiplayer AI will need to solve.
Multiplayer AI needs to move past the group chat phase. Chats are chaotic, everyone sees everything (creating social & management issues), and they're bad for long projects. Worse, they keep AI trapped inside existing teams, when its real promise is working & helping across them.
13
Good example of the long-tail of capabilities. There are so many things AIs can't do because we haven't asked them to and realized they lack the capability. This can be trained, it just hasn't been a priority.
On the train yesterday, table of middle aged women next to me talking about AI. All ChatGPT, pronounced "chat GBT", no idea why lol One of them was disappointed because she asked it to make a small crossword and it couldn't I thought surely not. I use these models every day, they do things in minutes that'd take me hours. So I got the app out and asked for one myself Every down clue is a copy of an across clue. "You ___ here" is apparently EST. The down answers are CET, ASE and TTN. Then it tells me its own puzzle isn't a proper crossword No wonder people outside tech think it's a fad. The stuff that blows my mind at work they'll never see, and the first thing they try falls over
13
I think I understand something until I write
You think you’re great at thinking until you write.
4
Ninajirachi radio on Spotify is good coding companion
14
When I'm deep in the agent coding flow, I forget to eat.
4
Checks email .... oh well.
Another 1000 invited today btw.
6
It's important to nurture the feeling in the belly that leads to that sparkle in the eye
My favorite kind of person is the curious nerd with a sparkle in his eye.
3
I gave GPT Astra a complement on some good work it did and it was just like "yes, I did that".
3
I got a fake news story Ad a couple of days ago. Like, literally, the ad was to a fake newspaper site that had a fake story about a politician. It was for some shady investment product. Never mind ugly, please remove scams.
Going forward, all advertising on 𝕏 will be subject to a reasonable esthetic standard. Advertisers who post ads that are ugly, shrill, strident or overstate claims about their product will be barred from advertising.
1
1
7
Super excited to see Ladybird come along. I wonder how much of this is driven by LLM agents?
2 months of performance work on @ladybirdbrowser 📈 we're gonna get this thing flying, one fix at a time!
6
Giving agents ViewOnly access to AWS + careful inline policies makes debugging prod infra issues significantly easier. A lot of this is just the fact AWS has a huge treasure trove of data that can be queried using the API. But agents make diving into that data a breeze.
6
My own experience is binges and burnouts
AI was supposed to make us work less I've never been this tired in my life most days I have up to 10 agents running at the same time. one fixing a bug, one writing pages, one refactoring something I already forgot I asked for, 3 other I have no idea what they are doing but i suppose i ask it? and I jump from conversation to conversation all day compared to 5 years ago, I probably context switch 100x more by the end of the day my brain is fried. completely toasted. nothing left, not even for the people I love I call it the fried brain effect thought it was just me but almost every founder I talk to lately says the exact same thing we got superpowers, and somehow the pressure only went up. if you can ship 10x more, you feel like you have to ship 10x more. every single day I don't have a solution honestly I have no idea where this goes from here anyone else feeling this?
2
Credit where credit is due
So cool seeing our weird UX experiments in T3 Code getting validated by the labs
12
Gemini Argon first impression: Smart model. Very supportive, positive, optimistic. I've always liked Gemini's personality and this model is no different. Nice to talk to. Seems very intelligent, at least comparable in general reasoning to the other frontier models. I haven't tested code capabilities.
12
Hard to argue with this, but I'd be interested in any counter opinions
there have not been fundamental advancements in alignment since RLHF. most of the stuff remains at the level of folk theory rather than scientific or engineering disciplines. the prediction that capabilities would race far ahead of interp and alignment has come true imo
1
52
My recent purchase of a Mac mini came with 3 month trial to Apple TV. Now I have to find what shows are worth binging so I can cancel after the trial.
21
Word of the day: mechanomorphism describing humans or animals in terms of machines
6
The future where the only IP left is the model weights themselves ...
I’m no longer sure what “intellectual property” means when intellect becomes free.
15
We live in a new world. How does this look so good, the expressions are so good
ok japan is serving me weapons grade ai content holy shit xitter.cf/tintinpapa1/status/210…
143