Juanjo do Olmo - e/acc

Pls don't take my RTs too serious.
185k+ Instagr followers (AI Drugs & Robots).
Medical AI Engineer @DOHsocial /@cursor_ai Ambassador/ BSc 💊/ AI @iia_es

[Juanjo do Olmo - e/acc @Claxterix]

Creo q voy a crear un hilo de hilos con cosas que he ido guardando en destacados a lo largo de mis años en Twitter ahí va el primero

Hilo sobre interesantísimas PARADOJAS:

https://t.co/adOgo9eK7r

[David Perell @david_perell]

Some paradoxes of modern life:

1. The paradox of reading: The books you read will profoundly change you even though you’ll forget the vast majority of what you read.

[Y Combinator @ycombinator]

Today we're launching Paxel: a free tool that analyzes your Claude, Codex, and Cursor coding sessions and gives you a profile of how you build with AI.

It runs locally inside Docker, and your code never leaves your machine.

Try it at https://t.co/HqSHneQSTQ

[Alex Albert @alexalbert__]

We just published internal data on how much of Claude's development is already being done by Claude:
- Over 80% of all code merged into our codebase is now written by Claude
- It's been months since many researchers at Anthropic hand-wrote code
- The typical Anthropic engineer ships 8x as much code as they did in 2024
- On the most open-ended engineering tasks, Claude's success rate jumped from ~26% to 76% in 6 months
- When research sessions went off-track, Claude proposed a better next step than the human took 64% of the time

We're not at recursive self-improvement yet, but it could come sooner than most expect. I highly recommend reading the full blog post.

[Gabriel Rufián @gabrielrufian]

A partir de cuántos "casos aislados" se pasa a ser organización criminal?

[Cursor @cursor_ai]

With canvases, Cursor can create apps like dashboards, reports, and internal tools.

Now you can publish a canvas and share it with your team via URL.

[Anthropic @AnthropicAI]

Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor.

It’s happening faster than we thought, and the implications deserve greater attention. https://t.co/OVVPJO7VQx

[OpenAI @OpenAI]

We’ve been researching new ways for ChatGPT memory to carry context across conversations and keep it useful over time.

Today, that work is rolling out as a more capable memory system in ChatGPT. https://t.co/0MyFKCe2Mu

[Carlos Santana @DotCSV]

Artículo muy interesante de Anthropic sobre como gracias a la IA están pudiendo agilizar su proceso de investigar y entrenar mejor IA.

O como coloquialmente se le llama: cerrando el bucle

[Juanjo do Olmo - e/acc @Claxterix]

Skill AIssue

[Wise @trikcode]

You basically need to be unemployed to keep up with all this AI stuff.

[Jorge Muñoz @libertad_indiv]

BASTOS en la TV totalmente desatado.

"¿Quién mata gente?"

[Mihura @XMihura]

lo de gpt5.5 xhigh es absurdo

es que es absolutamente ridículo lo que puedes hacer con este bicho por lo que cuesta una bolsa de cacahuetes

[Sk Akram @akramcodez]

this might be the best explanation I've ever heard

[Mark Kretschmann @mark_k]

New AI benchmark just dropped: ProgramBench.

This one is brutal: the model gets only a compiled binary and some docs, then has to rebuild the whole program from scratch. No source code. No internet. No decompilation.

Even the best models barely fully solve anything. Claude Opus 4.8 leads with 2 fully resolved tasks, GPT-5.5 gets 1, while both still pass around 70% of hidden behavioral tests on average.

This is exactly the kind of benchmark we need more of. Not toy coding. Actual software engineering.

[xAI @xai]

Meet Go by Gopuff and SpaceXAI: your personal shopping assistant that knows what you want and delivers in minutes.

Powered by Grok text, audio, and image models.

[OpenAI @OpenAI]

It's time to fly.

[Carlos Santana @DotCSV]

Lo dicho, un modelo que hace avanzar las capacidades de los modelos en abierto! 🔥

https://t.co/CyMCsrLeao

[Ideogram @ideogram_ai]

Introducing Ideogram 4.0: the best open image model in the world.

Think it. Make it. Own it.

Download the weights, fine-tune on your own data, and run it on your hardware. Live on every Ideogram plan and the API today.

[Sergio Hidalgo @SergioHidalAERO]

A mi me parece una locura. EEUU convence a los paises de la región para que le ayuden a atacar a Irán (logistica).Nadie quería por miedo a represalias. EEUU les convence diciendo que les va a defender. 2 meses después estamos en estas
La perdida de credibilidad es total

[shirish @shiri_shh]

Lovable CEO realizing their biggest model provider is now their biggest competitor.

[Andrew Ambrosino @ajambrosino]

a few months ago in an interview, someone asked me where we wanted to take the codex app. i answered with something along the lines of: we intend to make it the best app ever built for desktop, full stop.

it probably felt like a little much, but i meant it. and it feels less potentially hyperbolic now than it did then.

Codex is the best way to build software. it is now the best way to do many other things too. we will lean into both, and much of it will mean we blend a lot with ChatGPT. we will do this only when we can deliver something incredible and better than what the two separate current things can deliver alone.

we will also combine the best parts of cloud and local environments (and yes, windows+linux). and the best of instant responses and long-running objectives, like /goal. we will do so with Taste™

outside of the incredible gpt models, 3 things have made the Codex app what it is:
- an opinionated view of how agents should work with a high quality bar
- a tight and honest dogfooding loop
- you

those 3 things will continue to be P0.
LFG.

[Tibo @thsottiaux]

ChatGPT

Whether you understand the name or not. It's here to stay. It's the past, the present, the future. Synonym with AI, soon synonym with agents. Much to build.