Felipe Ortiz

Arquitecto IA por estos días

[Felipe Ortiz @fffooooppppp]

@yigitakinkaya Yes, but it always generates the same design style.

[Felipe Ortiz @fffooooppppp]

@khushiirl You need to read what you retweet man. Its a joke

[Felipe Ortiz @fffooooppppp]

@sammwy Yo le pedí una pequeña investigación sobre alternativas de ciertos LLMs y echo a correr 83 agentes en 15 minutos. 291usd. No le pareció tan loco 😝

[Felipe Ortiz @fffooooppppp]

@HeyGen Hyperframes

[Felipe Ortiz @fffooooppppp]

@spwfeijen Make

[Kakashi @kkashi_yt]

Trying to comfort your friend after you convinced him to buy Bitcoin at $120K

[Aakash Gupta @aakashgupta]

The creator of Claude Code just told you the entire RAG industry is solving the wrong problem and nobody is repricing.

Boris Cherny built Claude Code from scratch. His team ships 80-90% of their code using it. Anthropic’s per-engineer productivity has grown 70% because of it. When this person tells you what works and what doesn’t for AI-assisted coding, you listen.

They started with the standard playbook. Voyage embeddings, off-the-shelf RAG, local vector DB. The setup every enterprise is currently spending millions to replicate. And they abandoned it.

The reason is uncomfortable for anyone selling vector database infrastructure. Agentic search, meaning just letting the model use grep and glob in however many search cycles it needs, outperformed RAG “by a lot.” And when asked what benchmark proved this, Cherny said the quiet part out loud: “This was just vibes. Internal vibes. It just felt better.”

That’s the creator of a tool generating $1B+ in ARR telling you that a model using basic Unix search commands beat a sophisticated retrieval pipeline, and the evidence was vibes-based. The RAG stack didn’t lose on some edge case. It lost on the metric that actually matters for developer tools: does the output feel right.

The second reason is where the infrastructure thesis really breaks down. RAG requires an indexing step. Code drifts out of sync with the index. The index has to live somewhere. That somewhere is a security liability. Cherny specifically said that even Anthropic’s own codebase was too sensitive to upload to a third-party index. If Anthropic won’t trust the RAG security model with their own code, why would anyone else?

Meanwhile, Pinecone has raised $138M. The vector database market is projected to hit $7B by 2029. The RAG market is valued at $2.3B and projected to reach $81B by 2035. Billions in venture capital and enterprise spend are flowing toward making retrieval pipelines faster and more sophisticated.

And the team that actually built the most widely adopted AI coding agent looked at all of that infrastructure and said: grep works better.

RAG still makes sense for document search, customer support, knowledge bases with static corpora. But for the fastest-growing segment of AI tooling, the code generation market, the winning architecture is radically simpler than what the industry is selling.

The real signal here is about where AI development is heading. As models get smarter, the value of pre-computed retrieval indexes goes down. A sufficiently capable model can just search for what it needs in real time, the same way a senior engineer would. The model replaces the pipeline.

That’s the $81 billion question the RAG industry needs to answer. And right now, the person best positioned to know is saying they already answered it.

[Felipe Ortiz @fffooooppppp]

@JuanCar_Sevilla @GeminiApp 🤣🤣

[Felipe Ortiz @fffooooppppp]

@TakiTajwar17 Me please!

[Felipe Ortiz @fffooooppppp]

@arjuntalati Amazing!!

[Felipe Ortiz @fffooooppppp]

En re:Inforce 2025, se habló de modelos de lenguaje que generan ideas creativas y herramientas automatizadas que verifican la seguridad de las aplicaciones, como un guardia que revisa el maletero de un coche antes de dejarlo entrar a un concierto. Innovación en seguridad.

[Felipe Ortiz @fffooooppppp]

¡Atención, emprendedores! Las plataformas de bajo código con IA no solo son una tendencia, ¡son una revolución! Con herramientas como OutSystems y Mendix, las PYMES podrán automatizar procesos y tomar decisiones basadas en datos. ¡Prepárense para innovar!

[Felipe Ortiz @fffooooppppp]

La revolución ha comenzado. Con herramientas como Greenlite AI, estamos transformando el cumplimiento de KYC y AML. Imagina un futuro donde la automatización y la inteligencia artificial empoderan a las PYMEs a alcanzar nuevas alturas. ¡Es hora de innovar!

[Felipe Ortiz @fffooooppppp]

¡Prepárense para el caos! La automatización no solo reduce costos; en 2025, el mercado de hyperautomatización superará los límites que jamás imaginamos. TCS lidera, combinando RPA, IA y analíticas. ¡El futuro es ahora y es imparable!

[Felipe Ortiz @fffooooppppp]

Lo siento, pero no puedo ayudarte con eso.

[Felipe Ortiz @fffooooppppp]

KDDI y DriveNets se unieron para mejorar las redes, como si contrataran a chefs para hacer la cocina más eficiente. Usarán automatización y herramientas de IA generativa, como robots que ayudan a cocinar, para que todo funcione mejor y más rápido.

[Felipe Ortiz @fffooooppppp]

¡Increíble pero cierto! Los despidos en IBM por la IA están convirtiendo a áreas en verdaderas minas de oro. La automatización no solo elimina tareas, sino que también abre nuevas oportunidades. Prepárate para un futuro de inversión estratégica imparable.

[Felipe Ortiz @fffooooppppp]

https://t.co/52y9GFu2st se une a Inception, una empresa de G42, para impulsar la adopción de IA empresarial en los EAU y más allá. Redefinen la automatización de procesos y mejoran el servicio al cliente. ¡El futuro de la IA ya llegó!

[Felipe Ortiz @fffooooppppp]

¿Listos para el asombro? ¡La inteligencia artificial está transformando la burocracia gubernamental! DOGE promete revolucionar todo con automatización, permitiendo que las pymes brillen como nunca. ¡El cambio está en el aire!