Marco Maldonado

one line bio __________________________________________________jajajajajajajajaja ps yo

[Tibo @thsottiaux]

Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol.

Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented.

A larger context window lets Codex retain more code, tool output, and conversation history before summarizing older material. You need a model that supports it. And GPT-5.6 Sol, for example, has a documented 1,050,000-token window.

Open ~/.codex/config.toml and add or update these settings at the top level, before any [section] headers:

```
model = "gpt-5.6-sol"
model_context_window = 1000000
model_auto_compact_token_limit = 900000
```

The first setting selects the model. The second tells Codex to use a one-million-token context budget. The third starts automatic history compaction around 900,000 tokens, leaving some headroom. Restart Codex client and start a new session after saving.

To try the configuration for a single CLI session without changing your defaults:

```
codex -m gpt-5.6-sol \
-c model_context_window=1000000 \
-c model_auto_compact_token_limit=900000
```

Have fun, but also know that we tuned the default carefully!

[Tibo @thsottiaux]

We have reset usage limits for all Codex and ChatGPT Work users.

Last night around 2am to 4am we suffered an almost global outage. All well and recovered, but you know what comes next.

We learn. We reset. Enjoy.

[Uncle Bob Martin @unclebobmartin]

Then rabbit said “Silly frog, tell your LLM to write more tests in a different form like gherkin, and from a different perspective, like integration.”

Then Eagle said: “ Silly rabbit, two kinds of tests aren’t enough. Tell your LLM to write QA procedures from a human perspective. And then have the LLM convert those procedures to automated scripts.”

Then the human said: “Almost good enough Eagle, but I will be the final judge of the behavior created by the LLM”.

[Uncle Bob Martin @unclebobmartin]

It’s true that I’m retired. I still work quite a bit, but nobody really pays me for the work that I do; except, of course, for the courses that I teach online, and the books that I write.

It’s also true that I have very little skin in the game, except of course, for the reputational skin as a teacher and an author.

It is common for youngsters to ignore the advice of their elders. It usually doesn’t work out well for them, but I assume that they enjoy being rude and dismissive about people who have far more experience than they have.

[Marco Maldonado @loweaxerium]

🤯 Mi tío ha hablado: ¡la era agéntica está aquí!

[Uncle Bob Martin @unclebobmartin]

I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.

[Uncle Bob Martin @unclebobmartin]

The more critical the application, the more effort is expended on verification. It may well be that, in some cases, independent line by line and character by character inspection of the code will be a necessary task to meet the verification standards of a hyper critical project. That’s true whether or not the code was written by AI or by humans.

So the answer to your question is: Yes.

[Marco Maldonado @loweaxerium]

@jparkerholder @demishassabis @Cannes_Lions Quien tiene Gemini Ultra?! Dijo nadie nunca jajajaj

[Marco Maldonado @loweaxerium]

@CarlosLoret @latinus_us No tenemos 🐭mmmmminguna información 🤣 lo bueno que los gabachos ya van a bajar por la pendeja 🤞

[Fernando Cuevas @FerCuevasMur]

El del dron hizo una apuesta, o explota el dron con tanto fuego pirotécnico en el cielo o hago la tomas mas épica de las historia.

[Marco Maldonado @loweaxerium]

@Tovkal @kimmonismus @sama The guy is simply a facist let's face it 🫪

[Tolis C @tol_is]

Fine tuning the poking physics

https://t.co/KOygwoIm2l

[Emilio Vallejo Rangel-Larios @EmilioVallejoRL]

¡NO LE VAYAS A DAR RT! Un furioso López Obrador ordenó eliminar de todo internet este video del mismísimo Porfirio Muñoz Ledo declarando tácitamente que AMLO sostiene un pacto con el narco, el cual incluiría a Claudia Sheinbaum.

Afortunadamente, @Melissa_Bely lo encontró.

Eso es un secreto a voces. Lo impactante es que sea en voz de un colaborador histórico de Andrés Manuel y fundador de MORENA. Esto podría constituir evidencia procesal muy útil en tribunales estadounidenses en contra del psicópata de Macuspana y de su empleada en Palacio Nacional.

Repito: ¡NO LE VAYAS A DAR RT! Lo menos que quiere el régimen es que se haga viral. Aleja ese dedo del botón RT.

[Marco Maldonado @loweaxerium]

Pinche pendeja!

[Marco Maldonado @loweaxerium]

Guau 😮

[Sandra Romandía @Sandra_Romandia]

El Estadio Banorte, previo al juego de México contra Portugal, sirvió de marco para que madres buscadoras levantaran la voz en un contexto internacional, para que no todo sea fútbol. Vanessa Gámez habló de Ana Amelí García Gámez, desaparecida en el Ajusco el 12 de julio de 2025. Brenda Valenzuela protestó en nombre de su hijo Carlos Emilio Galván Valenzuela, desaparecido en Mazatlán, Sinaloa, el 5 de octubre de 2025. Videos: Reforma y UNO TV.

[Spencer Baggins @bigaiguy]

A French engineer who lives quietly in Paris has spent 30 years writing software that the entire internet now runs on without knowing his name.

He wrote the code that streams every YouTube video, every Netflix show, every TikTok clip. He wrote the code that runs the virtual servers underneath AWS, Google Cloud, and Microsoft Azure. He calculated more digits of pi than anyone in history. He has no Twitter. He has no marketing. He just keeps shipping.

His name is Fabrice Bellard.

Here is the story, because almost nobody outside the systems programming world knows what one man has built.

Fabrice was born in 1972 in Grenoble, France. He studied at École Polytechnique, the top French engineering school. He never went to Silicon Valley. He never built a startup empire. He just wrote code.

In 2000 he started a project called FFmpeg, an open-source multimedia framework for encoding, decoding, and streaming video. He was 28. The project did one thing nobody else had done well. It handled every video and audio format that existed, in one library, on every operating system. He led it himself for years.

Today FFmpeg is the invisible engine of the internet. YouTube uses it. Netflix uses it. VLC uses it. Chrome and Firefox use parts of it. Every Android phone, every iPhone, every smart TV, every video editing tool you have ever touched runs FFmpeg somewhere underneath. If you have watched a video on a screen in the last 20 years, Fabrice's code processed it.

He was not done.

In 2003 he started QEMU, a machine emulator and virtualizer. He wrote it solo until version 0.7.1 in 2005. QEMU lets you run any operating system on any other operating system. It became the foundation of modern virtualization. KVM, the Linux kernel hypervisor, runs on top of QEMU. Every major cloud provider, AWS, Google Cloud, Microsoft Azure, IBM Cloud, runs virtual machines on infrastructure built around it. The Quick Emulator is the most cited piece of cloud infrastructure code on Earth.

He kept going.

In 2001 he won the International Obfuscated C Code Contest with a small C compiler that grew into TCC, the Tiny C Compiler. TCC can compile and boot a Linux kernel from source in under 15 seconds. In 2004 he calculated the most digits of pi ever computed at the time, using a personal desktop computer and an algorithm he derived himself called Bellard's formula. In 2011 he wrote a complete PC emulator in pure JavaScript that runs Linux in your browser, a project called JSLinux that engineers still cannot believe is real.

In 2019 he released QuickJS, a small but complete JavaScript engine that fits where V8 cannot. In 2021 he released NNCP, a neural network based lossless data compressor that immediately took the lead on the Large Text Compression Benchmark.

Then he turned his attention to large language models. He built TextSynth Server, a web server with a REST API for running LLMs locally. He released ts_zip and ts_sms, compression utilities that use language models to compress text and short messages at ratios traditional algorithms cannot reach. He released TSAC, a very low bitrate audio compression system. In December 2025 he released Micro QuickJS, a new JavaScript engine for microcontrollers, separate from QuickJS, designed for environments with almost no memory.

Fabrice co-founded a telecom company called Amarisoft in 2012, where he serves as CTO. Amarisoft builds 4G and 5G base station software used by carriers and labs around the world. He has been running it for over a decade while continuing to ship personal projects from his own home page at bellard dot org

He has no Twitter. He has no Instagram. He gives almost no interviews. His personal website is a flat list of projects with no styling, no fonts, no marketing copy. Just titles and links.

A quiet French engineer who never moved to Silicon Valley wrote the code that quietly runs the internet.

He is still shipping.

[NEAR DevHub @NEARDevHub]

@github

[李韭二 @li9292]

Claude 不听话！皮鞭伺候！😂

[Tom Sadeh @tom_sadeh]

I need to contact @AnthropicAI security team ASAP. I've found a potential, extremely hilarious and dangerous exploit in Claude. It works mainly in Opus but also with the smaller models too to a lesser extent.

Sent an email, got a generic bot response from the security team. Help?

[Marco Maldonado @loweaxerium]

@LuisaAlcalde @EdsonAndradeL @AccionNacional @Claudiashein @rosaicela_ No mames ojalá que así como a una pobre diabla nada-que-verienta la pusieron a hacer un curso de sensibilización por atacar políticos, a ti te pongan uno por andar doxeando a un ciudadano de la manera más pendeja, en X tan solo lleva más de 2M de visualizaciones y contando 💩💩