Rémi Marenco (COG/ACC)

« 61. Should a seeker not find a companion who is his better or
equal, let him resolutely pursue a solitary course; there is no
fellowship with a fool. »

[Rémi Marenco (COG/ACC) @RemiMarenco]

« En outre, dans l’exercice de leurs fonctions, les membres du personnel sont tenus de faire preuve de manière générale de discrétion tant comportementale que vestimentaire,

afin de ne heurter aucune sensibilité et d’assurer le respect des opinions et convictions des clients, des partenaires et de l’ensemble des collaborateurs-collaboratrices au sein du collectif de travail. »

[Rémi Marenco (COG/ACC) @RemiMarenco]

Tellement triste...

https://t.co/hERXyBwwEQ

[Rémi Marenco (COG/ACC) @RemiMarenco]

Fun times avec les agents et la méthode BMAD.

[Rémi Marenco (COG/ACC) @RemiMarenco]

Sometimes, I think about how lucky we are to have ChatGPT, Claude, Gemini et al.

Having access to something is not diminished by how many people have access to it.

Same for drinkable water, it's quite surreal to think that we "only" need to push or pull something to have virtually unlimited water.

[Rémi Marenco (COG/ACC) @RemiMarenco]

Brownfield with the BMAD Method is so cool!

https://t.co/XIwO5kS5GZ

[Rémi Marenco (COG/ACC) @RemiMarenco]

Quelle chance d'avoir des transports en commun !

[GRITCULT @GRITCULT]

“The wise man does immediately what the fool does eventually.”

- Machiavelli

[Lewis Howes @LewisHowes]

Yes 🙏

[Literarium @Literarium12]

I have taken a bird out of a cage;
now the cage must be taken out of the bird’s heart.

- Umair Najmi

[Tech with Mak @techNmak]

Imagine trying to teach someone how to swim just by letting them read books about water.
That is how we have been training AI on physics, using text descriptions.

To really learn, you need to get in the water.

"The Well" is that water.

Polymathic AI has released a massive 15TB open-source library of physics simulations. It allows AI models to experience physical phenomena directly.

Instead of reading about a supernova, the model processes the actual data of the explosion. Instead of reading about aerodynamics, it analyzes the fluid flow.

This moves us from [Generative AI] (making things up) to [Scientific AI] (discovering truth).

A huge step forward for open science.

[ GitHub repo is in the comments ]

[Melodies & Masterpieces @SVG__Collection]

“It takes a long time to sound like yourself.”

— Miles Davis

[✒️ @Literariium]

Some of the coldest life advice you’ll ever hear

[Essential Mastery @EssentialMastry]

a reminder

[Akshay 🚀 @akshay_pachaar]

Microsoft did it again!

Building with AI agents almost never works on the first try.

You spend days tweaking prompts, adding examples, hoping it gets better. Nothing systematic, just guesswork.

This is exactly what Microsoft's Agent Lightning solves.

It's an open-source framework that trains ANY AI agent with reinforcement learning. Works with LangChain, AutoGen, CrewAI, OpenAI SDK, or plain Python.

Here's how it works:

> Your agent runs normally with whatever framework you're using. Just add a lightweight agl.emit() helper or let the tracer auto-collect everything.

> Agent Lightning captures every prompt, tool call, and reward. Stores them as structured events.

> You pick an algorithm (RL, prompt optimization, fine-tuning). It reads the events, learns patterns, and generates improved prompts or policy weights.

> The Trainer pushes updates back to your agent. Your agent gets better without you rewriting anything.

The best part: you can also optimize individual agents in a multi-agent system.

I have shared the link to the GitHub repo in the replies!

Let me know if I should cover this in a video demo!