Brian Rabil

2.2K posts

Brian Rabil banner
Brian Rabil

Brian Rabil

@brianrabil

Quit Goldman to mass-produce AI agents so I never have to work again.

Dallas, TX Katılım Temmuz 2020
298 Takip Edilen359 Takipçiler
Christoph Nakazawa
Christoph Nakazawa@cnakazawa·
Slop Cringe: When you let an llm write your blog posts. Don’t do it. It sucks, and it shows.
English
14
9
143
8.7K
Brian Rabil
Brian Rabil@brianrabil·
@rauchg I’m surprised you guys fell for the Salesforce meme to begin with.
English
0
0
0
26
Guillermo Rauch
Guillermo Rauch@rauchg·
Almost every SaaS app inside Vercel has now been replaced with a generated app or agent interface, deployed on Vercel. Support, sales, marketing, PM, HR, dataviz, even design and video workflows. It’s shocking. The SaaSpocalypse is both understated and overstated. Over because the key systems of record and storage are still there (Salesforce, Snowflake, etc.) Understated because the software we are generating is more beautiful, personalized, and crucially, fits our business problems better. We struggled for years to represent the health of a Vercel customer properly inside Salesforce. Too much data (trillions of consumption data points), the ontology of Vercel was a mismatch to the built-in assumptions, and the resulting UI was bizarre. We generated what we needed instead. When you don’t need a UI, you just ask an agent with natural language. We’ve also been moving off legacy systems with poor, slow, outdated, and inconsistent APIs, as well as just dropping abstraction down to more traditional databases. UI is a function 𝑓 of data (always has been), and that 𝑓 is increasingly becoming the LLM.
English
259
135
1.9K
830.2K
Brian Rabil
Brian Rabil@brianrabil·
@TBYSTweet Dallas devolved into a 3rd world shit hole. We are trying to get out.
English
0
0
0
90
Think Before You Sleep
Watching Texas get turned into a 3rd world country in just the 4 years that I have lived here has been one of the most black pilling experiences of my life. You don't hate politicians on both sides enough.
English
172
1.1K
10.2K
127.3K
Brian Rabil retweetledi
kache
kache@yacineMTB·
you still need to read and understand code
English
219
266
3.6K
136.4K
Brian Rabil retweetledi
dax
dax@thdxr·
please shut the fuck up i don't even care about the specific thing you're saying i'm just so tired of hearing predictions one after the other telling me what the future is going to be like just please shut the fuck up
English
404
901
14.8K
615.1K
Brian Rabil retweetledi
Bartek Radziejewski
Bartek Radziejewski@radbar_1·
It's unbelievable how daily morning stand ups where disrupting my mornings. Now few months into freelancing i can't look back
English
7
4
92
74.2K
Om Patel
Om Patel@om_patel5·
this guy vibe coded a wallpaper that shifts perspective when you move your head uses your webcam to track your position. move any direction and the background moves with you
English
108
124
2.6K
168K
graham harwood
graham harwood@grahamharw30844·
Sequential automation is the old way. •Agent A does Task 1. •Wait. •Agent B does Task 2. In a "Coordinator" architecture, you deploy a Swarm. Instead of waiting, one "Lead Agent" routes goals to specialists simultaneously.  Parallel execution isn't just faster—it's 80% more efficient.
English
5
5
94
151.1K
Santiago
Santiago@svpino·
I don’t read AI generated code. I don’t read AI generated tests. If AI says everything is good, I ship to production. This is a flawless strategy.
Moses Xu@mosesxu

@svpino i don't read every line CC writes for me. i define what needs to be tested and CC writes the tests too. if they pass it ships. "i understand every line in my codebase" was already a lie before AI showed up, now we just can't pretend anymore

English
65
9
271
42K
Mario Filho
Mario Filho@mariofilhoml·
peak unemployability is getting rejected by an underpaid position that I am theoretically one of the few people in the world qualified for 😂
Mario Filho tweet media
English
44
82
7.6K
484.6K
Lee Robinson
Lee Robinson@leerob·
I'm a big believer in open source, especially as AI improves. It was a miss to not mention the Kimi base in our blog from the start. We'll fix that for the next model 🙏 Their team clarified our usage was licensed in the tweet below. x.com/Kimi_Moonshot/…
Kimi.ai@Kimi_Moonshot

Congrats to the @cursor_ai team on the launch of Composer 2! We are proud to see Kimi-k2.5 provide the foundation. Seeing our model integrated effectively through Cursor's continued pretraining & high-compute RL training is the open model ecosystem we love to support. Note: Cursor accesses Kimi-k2.5 via @FireworksAI_HQ ' hosted RL and inference platform as part of an authorized commercial partnership.

English
208
110
2.3K
393.8K
Josh tried coding
Josh tried coding@joshtriedcoding·
writing an article about AI SDK v6 running AI agents in isolated containers with their own filesystem and shell access 👀
Josh tried coding tweet media
English
13
5
157
8.6K
Ian Curtis
Ian Curtis@XRarchitect·
Testing off-axis projection demo. Basic scene layout in Blender glb -> detailed splat via World Labs Three.js for engine MediaPipe for face tracking Next step is to add a character you can move around in the environment
English
229
458
5.6K
423.2K
Brian Rabil
Brian Rabil@brianrabil·
@Bencera My workflow as well. I also recommmend throwing the plan in ChatGPT pro.
English
0
0
0
62
Ben Cera
Ben Cera@Bencera·
my AI coding workflow as a solo founder: - opus 4.6 for exploration + planning - codex 5.4 xhigh to stress-test the plan (catches gaps opus missed) - back to opus, which usually complains codex is overengineering lol - few rounds back and forth. codex implements, opus reviews. - ask both: "safe to ship? what's the worst thing that could happen?" opus and codex arguing over my codebase is my entire engineering team. will probably ship this workflow as a Polsia feature at some point.
English
93
32
560
33.6K
Brian Rabil retweetledi
james hawkins
james hawkins@james406·
what is your 5 prompt plan? where do you see yourself in 5 prompts?
English
50
42
525
27K