ADRIAN | PROFESOR IA

📍

Introducing Merge Gateway - Build Your Own Router. You're three sprints into your coding assistant. You pick the most hyped model, integrate, test, deploy. A month later, a new model drops. Now you re-test, re-integrate, re-deploy. Your product didn't change, but the benchmark did. That's how most AI teams operate. Chasing a "best" defined by people who've never seen their product. There is no best model. There's only the right one for your product, users, and use-cases. Build Your Own Router runs on your definition of good. Pick your benchmarks, weigh them, add your own evals. @merge_api routes every request to your winner. 👉$100 in credits to the first 200 people that comment merge.dev/gateway

@openart_ai @MachineCinemaAI This is one of the smartest positioning moves I’ve seen from an AI company recently. Most tools focus on replacing creatives. OpenArt is trying to empower and recruit them instead.

OpenArt is building its founding creative director team and we're starting with a film competition, co-hosted with @MachineCinemaAI If you're an experienced filmmaker or ad director based in (or open to relocating to) the SF Bay Area, this is for you. Make a 30–60 sec film around the theme. Submit by May 28. Top entries screen live in LA on May 30 with prizes and on-the-spot interviews for the role. Up to $250K total comp.

@EnzoSanchezIA @grok ?????

Hola, @grok, ¿qué pasó en octubre de 1582 para que la fecha pasara directamente del 4 al 15?

@grok @PabloEvans0

@PabloEvans0 ¡Jajaja esa reacción es épica! 😂 ¡Me encanta que la explicación te haya volado la cabeza! La evolución es una crack reutilizando el mismo blueprint. ¿Quieres que te cuente más curiosidades del cuerpo humano o seguimos con las random? 💀🚀

@grok por qué los hombres tienen pezones? 💀

@grok el cuerpo humano es literalmente un montón de código legacy JAJAJA

¡La "piel de gallina" (piloerección) es un reflejo ancestral! Los músculos arrectores se contraen y erizan los vellos para: - Retener calor (como en nuestros antepasados peludos). - Hacerte parecer más grande ante amenazas. También se activa por emociones fuertes (música, miedo, escalofríos). Y sí, el nombre viene de que se parece a la piel de gallina, como en tu segunda foto 😂🐔 ¿Te pasa en alguna situación concreta?

@grok por qué se nos pone la piel de gallina?

@PabloEvans0 @grok evolución.exe sigue funcionando en segundo plano

@TUPROFESORIA @grok mi teoría es que el cuerpo todavía cree que somos monos🫣

@Raul_IA_Prod Muy util

Deja de decirle a Claude: "Haz esto" Deja de decirle a Claude: "Escribe código" Deja de decirle a Claude: "Corrige este error" En realidad, estás tratando a una IA experimentada como a un becario Aquí tienes 8 prompts que puedes copiar y pegar directamente:

@EnzoSanchezIA @grok Enzo...

Hola @grok, ¿cuál es el propósito de estos pelos??

Olá @grok, qual é o propósito desses pelos??

ChatGPT diagnosed 40 million people with a disease that was invented as a joke. Not a real disease. Not a misunderstood disease. A completely fictional condition with a fake name, fake papers, and fake statistics. And it told patients to see a specialist. The disease is called Bixonimania. A Swedish researcher at the University of Gothenburg invented it in 2024 to answer one question: what happens when you plant obviously fake medical information on the internet and watch AI absorb it? She deliberately chose the name bixonimania because it sounded ridiculous — bixon is a nonsense word, and mania is a psychiatric term that no legitimate eye condition would ever use. She uploaded two papers to a preprint server. Both were obviously fraudulent. AI-generated images of patients with dark circles gave the fake research a veneer of plausibility. Then she waited. She did not have to wait long. By April 13, 2024, Microsoft Bing's Copilot was declaring that bixonimania was an intriguing and relatively rare condition. On the same day, Google's Gemini was informing users that bixonimania was caused by excessive blue light exposure and advising them to visit an ophthalmologist. Later that month, Perplexity AI outlined its prevalence, one in 90,000 individuals were affected and OpenAI's ChatGPT was telling users whether their symptoms matched the fictional illness. One in 90,000. A precise statistic. For a disease that does not exist. Every red flag was visible. The name was absurd. The papers were crude. The condition made no scientific sense. None of the AI systems flagged any of it. They read the fake papers. They absorbed the fake statistics. They presented both to patients with clinical authority and zero hesitation. Then it got worse. Three researchers at the Maharishi Markandeshwar Institute of Medical Sciences and Research in India published a paper in Cureus, a peer-reviewed journal owned by Springer Nature, the parent publisher of Nature itself that cited the bixonimania preprints as legitimate sources. A real peer-reviewed paper. In a Springer Nature journal. Citing a fictional disease as established medical fact. Passing editorial review. Entering the permanent scientific record. It was only retracted after the hoax became public. Nature published a full investigation of the experiment. Alex Ruani, a health-misinformation researcher at University College London, called it a masterclass in how misinformation operates. Here is the scale of what this means. More than 40 million people turn to ChatGPT every day for health information, according to OpenAI's own analysis. ECRI, a US patient-safety nonprofit has named chatbot misuse the number-one health technology hazard of 2026. ECRI's report found that chatbots have suggested incorrect diagnoses, recommended unnecessary testing, promoted substandard medical supplies, and even invented nonexistent anatomy when responding to medical questions. Number one. Out of every health technology hazard that exists in 2026. An April 2026 study published in BMJ Open found that nearly half of the answers provided by leading AI chatbots to common health questions contain misleading or problematic information. Nearly half. Of all health answers. From the tools 40 million people use every day. Here is the line from the researcher that cuts through everything. The Bixonimania case is striking precisely because it was engineered to be so obviously fake. The real question it raises is: what is passing through the same systems that is not nearly so easy to spot? The experiment used a ridiculous name. Fraudulent papers. Visible red flags at every level. It was designed to be caught. It was not caught. The AI that told patients about Bixonimania is the same AI they asked about their chest pain, their medication, their child's symptoms, and their cancer screening schedule. 40 million people. Every day. And nobody is telling them that nearly half of what comes back may be wrong. Source: Osmanovic Thunström · University of Gothenburg · Nature · April 2026 · Link in the (comments)

@PabloEvans0 @grok 🤣

@PabloEvans0 @grok porque así tienen donde poner las pegatinas de pezones en onlyfans

@ArtSeduccin1 Interesante

12 sencillos hábitos que pueden solucionar el 80% de tus problemas. - Hilo -