Antonio Diêgo ➔ orglabs.vercel.app
@antoniodiegoluz
Followers
81
Following
60K
Media
26
Statuses
1K
Licenciado em Matemática • Sistemas de informação IFBA Java | PHP | React Developing personal organizer apps at @org_labs
Feira de Santana - BA, Brasil
Joined September 2013
“Whenever you think that some situation or some person is ruining your life, it’s actually you who are ruining your life. It’s such a simple idea. Feeling like a victim is a perfectly disastrous way to make go through life.” — Charlie Munger
49
509
4K
I built an infinite AI chess game, powered by: ▪️ AI SDK for a single DX to all frontier models ▪️ AI Gateway for seamless access with 1 API key ▪️ Workflow to keep the game going forever Right now Anthropic is playing OpenAI: https://t.co/TdZ57Qpej6
152
107
2K
0
0
1
Attention: this might be the video that opens the door to the future. When a SOTA agent model connects to a robot dog with no remote control— MiniMax M2.1 × Vbot, super-powered in action. A model trained in the virtual world now controls a robot in the physical world. Hello,
28
128
682
My 2025 @v0 Vibecheck: 3 prompts, 2 chats, 1 days active 🏆 9-to-5er, Rising Star Get yours at
v0.app
See your year in review on v0 - achievements, stats, and highlights from 2025.
0
0
0
Agora temos algo como se fosse uma maior separação de responsabilidade, cada alteração é uma peça granular
0
0
0
O Cursor ficou bem melhor com nova guia de agentes. Agora podemos definir um novo agente com uma função ao invés de manter longas conversas e fazer várias alterações num chat, o que ficava difícil de retornar e ter controle depois.
1
0
0
Coding with AI vs coding without AI. How true is this?
302
211
4K
X algorithm, only show this to people who is into > mathematics > machine learning > quantum physics > neurology > economics @grok I need more of these people on my timeline.
1
0
0
Be honest, what actually gets you hired faster in tech? • Strong portfolio • Networking • Certifications • Pure luck Let's be real, please.
423
39
843
For the first time, an AI model (GPT-5) autonomously solved an open math problem submitted to our benchmarking project IMProofBench, with a complete, correct proof, without human hints or intervention. A small but novel contribution to enumerative geometry. Some background:
43
252
2K
Wow😲! The visual explanation of integration in calculus.
54
802
7K
GPT Image 1.5’s IQ is far behind Nano Banana Pro. It fails the math problem here (left: GPT, right: 🍌), also other math/physics/maze problems. Nano Banana Pro is a multimodal built on Gemini 3 Pro. I suspect GPT Image 1.5 is still stuck on the older GPT-4o architecture.
8
3
122
@predx @MiaAnabadie E o que uma impressora disse para outra impressora? . .. .. “Essa folha é sua ou é impressão minha?”
0
6
89