Persiscal retweeted
What does one AI conversation actually cost?
Most founders scaling an AI product can't answer that.
I wrote up the real numbers: tokens, caching, routing, and the hidden costs nobody budgets for 🧵
Persiscal retweeted
In the next version of Claude Code: run /usage to see a breakdown of which Skills, Agents, MCPs, and Plugins are using your tokens
CLI today, coming to Desktop next
Persiscal retweeted
First project I I was involved in shipping! 🚢
Free token, API credits and security scanner for hard working open source maintainers.
We’re launching Codex for Open Source to support the contributors who keep open-source software running.
Maintainers can use Codex to review code, understand large codebases, and strengthen security coverage without taking on even more invisible work.
developers.openai.com/codex/…
Persiscal retweeted
Fun fact: OpenAI handles 800 million users on ChatGPT with just one PostgreSQL primary and 50 read replicas 🤯
Today, OpenAI published an engineering blog explaining how they scaled their Postgres setup to support a massive 800 million users using a single primary and 50 multi-region replicas.
They dive into details around their scaling approach, the PgBouncer proxy, cache locking, and cascading read replicas. It is genuinely neat and impressive.
I just published a video on my YouTube channel where I dissect the blog and break down the nuances.
Give it a watch - it is short and fun.
Persiscal retweeted
🤯 Ayer OpenAI sacó un post con como escalan PostgreSQL para millones de queries por segundo para 800 millones de usuarios de ChatGPT.
Usan UNA sola instancia primary + ~50 réplicas de lectura. Para las escrituras masivas tienen entre medias un CosmosDB. Es decir, tienen una instancia primary pero obviamente no le tiran todas las escrituras de golpe ahí.
🤔 A nivel de infra me encanta el diagrama de la imagen. Básicamente para poder balancear tráfico entre sus réplicas de lectura están usando pgbouncer desplegado en Kubernetes. Las DBs están desplegadas sobre el servicio de Postgres de Azure.
Obviamente el sistema de replicacion que han montado para tener “zero lag” como dicen ellos tiene su miga. Me hubiese gustado conocer más detalles ya que por lo que cuentan parece un sistema muy custom. No están usando la replicacion “normal” de los clusters de Azure.
Persiscal retweeted
Cowork just organized 6 months of receipts into a categorized spreadsheet with monthly breakdowns.
Pointed it at a folder. That’s it.
Persiscal retweeted
🚀 Amazing initiative by @every!
A powerful chance to fast-track your journey — from zero to digital products with real experience.
I recruited the best vibe coders I know for an all-day livestream on January 22.
@OfficialLoganK, @ryancarson, @bentossell, @fkpxls, @nateliason, @ashebytes, and the @every team—building live, sharing exactly how they work.
Free and open to everyone: every.to/go-agent-native
Persiscal retweeted
RT @frbautn: Se encuentra abierta la inscripción a maestrías y especializaciones de posgrado @frbautn para 2017 ow.ly/tFOq306LbMo
Persiscal retweeted
Estamos llegando a los 40.000 seguidores! Solo el 5% son "fake". Queremos agradecer a todos, nuestros no "fake" y fieles seguidores! GRACIAS
Persiscal retweeted
Google abrió su primer centro de emprendedores en Latinoamérica en Brasil ln.is/emprendedoresnews.com/…
Persiscal retweeted
PENSAR EN GRANDE! “Hay que animarse a pensar en grande” via @emprendedoresnews ln.is/emprendedoresnews.com/… #Entrepreneur #Mindset #mentoring
Persiscal retweeted
Un honor estar representando a la @frbautn en el Congreso Mundial de Scholas


















