Pierre Haas

Stealth - looking at ways to improve LLMs and AI Agents

[Pierre Haas @haaspierre_]

@pacovilletard lfg 🚀

[Pierre Haas @haaspierre_]

@zephyr_z9 Or even more people use these tools? Or people get multiple accounts (running on a few for tokenmaxxing)

[Vassili de Rosen 🦄 @Vassivasss]

https://t.co/UZN6y6bEim

[Pierre Haas @haaspierre_]

@Vassivasss Claude code

[AVB @neural_avb]

https://t.co/QeozQY6lRH

[Citoyen Informé @CitoyenInforme_]

Les municipales c’est demain

[Avid @Av1dlive]

https://t.co/To0OoOKYiZ

[Citoyen Informé @CitoyenInforme_]

Je vous jure l’appli « Citoyen Informé » est top…

Le tinder des municipales dispo sur IOS et playstore

[Pierre Haas @haaspierre_]

@CitoyenInforme_ @Vassivasss Ahah, mon pauvre

[Pierre Haas @haaspierre_]

@Yampeleg @kr0der I read xhigh is mostly recommended for long-running tasks and doesn’t perform better then high. OpenAI even said high beats xhigh on many tasks
Personally been using high

[Citoyen Informé @CitoyenInforme_]

Citoyen Informé : le Tinder des Municipales de Paris

[Citoyen Informé @CitoyenInforme_]

Citoyen Informé

[Pierre Haas @haaspierre_]

@iomancer @LLMJunky For sure, wasn’t the case for me

[Citoyen Informé @CitoyenInforme_]

Télécharge l’app dès maintenant: https://t.co/4AUDi6mm9D

[Pierre Haas @haaspierre_]

@LLMJunky and pushes back a lot compared to codex, which is nice when you are uncertain of the best path to action / best implementation

[Pierre Haas @haaspierre_]

@LLMJunky Looking good so far! Not noticing such a difference compared to Codex 5.3
Doesn't handle sub-agents as good as codex models yet

[Pierre Haas @haaspierre_]

@kamath_sutra Doesn’t OpenAI have their own speech-to-speech model? And what you are describing is inaccurate?

[Pierre Haas @haaspierre_]

@LLMJunky I love how they just dropped 5.3 instant and are teasing 5.4 in hour later 🤣

[Pierre Haas @haaspierre_]

@LLMJunky Check this out, built over the weekend
Loved the guide and repo with examples! Easy to follow and worked straight away. Need to have a look at your new articles, haven’t found the time yet

[Vassili de Rosen 🦄 @Vassivasss]

What if AI could see the world the way we do?

That’s the idea we bet our weekend on at the Mistral Worldwide Hackathon.

With @haaspierre_ and Arman Artola-Zanganeh, we built 𝗣𝗼𝗿𝘁:𝗪𝗼𝗿𝗹𝗱🌍, an open-source framework that lets anyone connect their Meta glasses to any AI system.

Let me take you back to saturday morning.
So before knowing it could work we needed the hardware.

So I ran to Rue de Rivoli and bought €500 Meta glasses on the spot.
If that’s not commitment, I don’t know what is (a true bet).

We then built non-stop for 36 hours to make it usable. End-to-end.
The glasses stream what you see → the AI makes sense of it → it answers back through the glasses’ speaker.

And suddenly when we understood that it was going to work, the question changed.

It was no longer “𝗜𝘀 𝘁𝗵𝗶𝘀 𝗱𝗼𝗮𝗯𝗹𝗲?”
It became “𝗪𝗵𝗮𝘁 𝗰𝗮𝗻 𝗽𝗲𝗼𝗽𝗹𝗲 𝗯𝘂𝗶𝗹𝗱 𝘄𝗶𝘁𝗵 𝘁𝗵𝗶𝘀?”

- A plumber getting live assistance while repairing something.
- A technician repairing industrial machinery.
- A traveler exploring a new country.
- A visually impaired person navigating space.

At first, we were looking for the “right” use case.

Then we realized something more interesting.
If AI can share your perspective, continuously, the use cases are not ours to decide.

That’s why 𝗣𝗼𝗿𝘁:𝗪𝗼𝗿𝗹𝗱🌍 is fully open source.

If you want to connect your Meta glasses, plug in your own models, customize with your own prompts, your own MCP, your Openclaw… you can.

Link to the open source repo (you can contribute and give it a little star ❤️): https://t.co/UueLnkMZpM
Link to the demo video: https://t.co/qcTDqKGvax

Huge thanks to the organizing team of the hackathon, it was truly great. @Jthmas404