Sabitlenmiş Tweet
🎯 Excited to announce the launch of @Arrow_Payments — today we’re emerging from stealth and setting out to build the most important company in US history.
👇👇👇
English
Yash Joshi
1.2K posts
Yash Joshi
@Ydj79
Co-Founder & CTO @Arrow_Payments — Revolutionizing healthcare payments
NYC Katılım Mart 2011
432 Takip Edilen360 Takipçiler
@gregpr07 I have been switching around. Codex is horrible with UI and Claude is horrible with writing compact code.
English
Who actually uses Codex over Claude Code? Claude Code is just 100x better imo, like the DX is WAY better.
English
@MaxMusing @linear Yeah game changer! It provides summaries on the left panel about what has changed so you can click on that and shows you relevant code.. that way you don’t have to read through the several lines of boilerplate and can focus on the main logical flows
English
man, the new @linear review feature is actually good.
I can finally work with 10k+ line diffs. still laggy in a few places but miles ahead of GitHub and Graphite.
English
Theo says his anti-Anthropic content has cost him money and sponsors. The X data shows it's delivering 60× more impressions than his pro content does.
He claims pro-Anthropic content always outperforms anti. Tested it on 800 of his posts (Feb 17 to Apr 30).
Volume: 4 truly pro vs 86 anti.
Per-post likes: pro narrowly wins (2,466 vs 2,075). He's right about that part.
Per-post views: anti pulls 2.8× more.
Total reach: pro 460K, anti 27.5M.
Sponsors price by impressions. He's losing the metric that pays.
On "ALWAYS outperforms": false. 49 of 86 anti posts beat his weakest pro in that period.
Caveat: X engagement only.
The letter making this claim is itself one of his top-3 anti posts. 6,756 likes. 1.27M views. And couniting.
Theo - t3.gg@theo
A letter to my friends at Anthropic I hate that I feel obligated to do this. I hate that I've had to be so harsh towards Anthropic for the past few months. I really, really don't want to. I know it might feel like I'm doing this for clicks or something, but I promise I'm not. My pro-Anthropic content ALWAYS outperforms my anti-Anthropic content. I have cost myself a lot of money, opportunities, sponsors, and more. I'm doing this because you work for an evil cult. I'm begging you to wake up. Your CEO, Dario, does not respect engineers. This is obvious. He couldn't make it more obvious if he tried (and I think he's trying pretty hard) You know this, but you don't want to acknowledge it. It has kept you up many nights. You know that bad code is shipping to users. You know that one bad tweet might get you fired. You fear for your vesting schedules. You're afraid. Nobody deserves what you're going through right now. You go to work afraid, you leave work afraid, and you go to YouTube to keep up on the dev world, just to hear me yelling all about how evil your company is. You deserve better. You might not feel like you do, but you know deep down that this isn't right. I hope you know how deeply I feel for you. I'm sorry. I know I haven't helped you much individually, and I want to be better about this. If you're ready to leave, please hit me up. I swear I'll never tell a soul. I have friends at every lab and most startups in the AI world. Most of them would be down to match your current vesting schedules, possibly even go beyond. If you're staying for the money, I beg you to hit me up. We can make the money happen somewhere that hates you less. I know I'm asking for a lot of trust here, and that you're scared after seeing how hard I've been on Anthropic. I can't blame you at all for that. I should have posted something like this months ago. That's my failure to own and I will own it to my best ability. If you're willing to trust me in this moment, I can make it right. Let me help you escape. You deserve to work somewhere that you can have impact. Somewhere that listens when you feel something is wrong. Somewhere that won't fire you when you point out the things that hurt your users. My DMs are always open to you. When you're ready, let me know. I promise to make it right.
English
@justinsunyt Yeah kanban is too bloaty! I think a project wise todo list with statuses is the way to go.
Some people are trying to do spec driven delelopment where the agents just add their thoughts for each requirement directly in the spec. Feels like that could be interesting
English
kanban doesn’t make sense for coding agents
we tried it 6 months ago. every task just ended up in the “needs review” column
Muhammad Zahid@mzahidtech
🚀 This is wild. @cursor_ai just dropped a Linear-style Kanban board where you can literally drag in tasks and Cloud Agents pick them up, work on them, open PRs, and ship results. Built with the new Cursor SDK. Full agent orchestration in one dashboard. Mind officially blown.→ Check the example: github.com/cursor/cookboo… #Cursor #AIagents
English
@theo Build an event bus and let them work as a panel to work through a problem.
English
It's so hard to describe the vibe difference between Opus 4.7 and GPT 5.5 (for coding)
GPT is smarter and can unblock you, but it gets stuck in stupid ways and strangles itself with context sometimes.
Opus will go down the most insane paths and refuse to acknowledge obvious answers, but it understands intent better and has more taste.
Whenever I use one for more than an hour, I always reach to the other to "clean up".
Best part? All of this changes every few weeks 🙃
English
Nobody wants to admit it but "vibecoding" works until your app has actual users. Then you discover what senior engineers have been getting paid for.
English
@theo How are you thinking of showing sub processes that mama claude spawns?
I think adding them as a process hook on the left panel would be neat
English
@theo I have missed being able to view all the tool calls the models make in a good view.
The best way to tell if the agent is BSing
English
It's insane how quickly T3 Code has progressed. Huge shoutout to Julius and all our open source contributors. Never thought we'd get this far
English
Learnt that Opus 4.7 will not verify things depending on your prompt
"Is my migration successful?" > No tool calls. Current context used
"Verify my migration is complete" > Will make tool calls
Opus 4.5 was eager to make tool calls, possibly due to a small context window.
English
@justbyte_ I did and totally. Just do it.
I think claude just treats me like I don't know shit explaining things with 5 million tokens.
If I were to switch back to claude I would have to add somethings in my claude.md to ask it to not explain things like I am 5 lol
English
@ParthJadhav8 I have my own version of this vibe coded in a few hours called autocoder. Doesn’t look as nice NGL
English
This is crazy !!
Cursor now has built a Kanban board where you can just drop in tasks and the agent will pick those up and complete them.
English
@ParthJadhav8 There are so many companies that are doing this in all different formats. The problem still remains the same, human bottlenecks in review and the actual spec.
English
@Ydj79 It’s just a demo project they published with the SDK, Might not become a full fledged product on its own.
So, please continue working on yours there will be a market for it
English
@curiousharish You don't use aws CLI? Just give that cli access to claude and let it cook
English
Someone please build a wrapper on AWS! Most confusing interface ever.
English
@RhysSullivan Review is extremely hard. I have tried a few spins of different things currently trying to build an agent that is spec aligned. Trying to use MDD and BDD to review easily
English
has anyone built "the software factory" thing, misc requirements:
- able to use my subscriptions (codex / claude)
- stacked diffs w/ graphite
- able to go from planning -> lots of small tasks
- closing the review loop
don't love current agent interfaces, want something new
English