Enrique oriol (@enrique_oriol) 's Twitter Profile
Enrique oriol

@enrique_oriol

Principal Lead Product Engineer at @Dynatrace. Love technology, innovation and startups. I used to blog.

ID: 583067906

linkhttps://enriqueoriol.com calendar_today17-05-2012 19:34:54

2,2K Tweet

866 Followers

613 Following

Santiago (@svpino) 's Twitter Profile Photo

These are some of the most mediocre people: The same folks who hate unit tests are now up in arms against writing evals for their LLM-based applications. If you are a solo developer or a startup building a prototype, you shouldn’t spend your time writing tests or evaluations.

Anshuman Mishra (@heyyanshuman) 's Twitter Profile Photo

I rejected a job offer yesterday. Not because of the salary. Not because of the tech stack. Not even because of the long hours they warned me about. But because, when I asked how they evaluate their AI systems, the hiring manager said: "We just ask it some questions and

Vlad Mihalcea (@vlad_mihalcea) 's Twitter Profile Photo

As a software engineer, it's very important to learn about Gall’s Law, which states that complex systems cannot be created successfully from scratch. In reality, even large systems, such as Netflix, Google, or Facebook, have started small and built incrementally over the

As a software engineer, it's very important to learn about Gall’s Law, which states that complex systems cannot be created successfully from scratch. 

In reality,  even large systems, such as Netflix, Google, or Facebook, have started small and built incrementally over the
Santiago (@svpino) 's Twitter Profile Photo

You have 3 choices when building AI agents: 1. If you want reliability, you'll sacrifice speed and cost. To improve the quality of your system, you can add guardrails, retry loops, human-in-the-loop checks, better and larger models, redundancies, etc. Better quality costs more

Andrej Karpathy (@karpathy) 's Twitter Profile Photo

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in

Enrique oriol (@enrique_oriol) 's Twitter Profile Photo

Building has always been the easy part for me Talking about what I build? Not really. Trying to break that pattern, so today I launched a side project on Product Hunt Part product, part personal experiment First time posting here. Let’s see what happens #buildinpublic

Enrique oriol (@enrique_oriol) 's Twitter Profile Photo

Product Hunt takeaway: The problem isn’t generating content anymore, AI already solved that and there's plenty of tools. The problem is the energy and time consistent marketing consumes while you’re busy building your actual business. That’s the gap I’m exploring #buildinpublic

Enrique oriol (@enrique_oriol) 's Twitter Profile Photo

Not everyone wants to get good at marketing, even though they know it’s important for growth. Some people just want it off their plate, so they can focus on building a better product and a real business. That’s who I’m building for. #buildinpublic

Enrique oriol (@enrique_oriol) 's Twitter Profile Photo

Playing with two different copies for my hero The first one feels bold but a bit abstract The other is simpler and clearer I keep going back and forth between them... WDYT? #buildinpublic

Playing with two different copies for my hero

The first one feels bold but a bit abstract
The other is simpler and clearer

I keep going back and forth between them...

WDYT?
#buildinpublic
Codely ﹤🍍﹥ (@codelytv) 's Twitter Profile Photo

WebMCP es lo mejor que le ha pasado a HTML desde HTML5. Es un nuevo estándar para que los agentes puedan interactuar con nuestras webs. Y lo mejor de todo es que lo han hecho de la mejor forma posible: expandiendo las capacidades del HTML. Con solo añadir dos nuevos atributos

Miguel Ángel Durán (@midudev) 's Twitter Profile Photo

Vivimos en un capítulo de Black Mirror. ① Un bot de OpenClaw hace una PR a matplotlib ② El maintainer la rechaza por ser un bot ③ El bot se enfada y escribe un artículo en su blog para avergonzarle públicamente La IA metiendo presión social. Qué grima.

Vivimos en un capítulo de Black Mirror.

① Un bot de OpenClaw hace una PR a matplotlib
② El maintainer la rechaza por ser un bot
③ El bot se enfada y escribe un artículo en su blog para avergonzarle públicamente

La IA metiendo presión social. Qué grima.