iiinova — where your digital self keeps evolving

Eschnou @eschnou.com · 02/12/2025

What? @drmichaellevin.bsky.social is back on @lexfridman.bsky.social with a 3 hour podcast 🤩 - the first one is still my #1 in my top episode list. If you have never heard of his work on bioelectricity and regenerative medecine. Time to catchup! www.youtube.com/watch?v=Qp0r...

youtube.com

Michael Levin: Hidden Reality of Alien Intelligence & Biological Life | Lex Fridman Podcast #486

YouTube video by Lex Fridman

Eschnou @eschnou.com · 29/09/2025

Are your development team embracing AI Native Development? What is the best next step in your journey? I've built a simple tool to assess your AI Dev maturity with 12 simple questions! aidevscore.com Feedback welcome! Ping me for help moving forward! #ainativedev #genai #aidev #agentic

aidevscore.com

AI Native Development Maturity Assessment

Evaluate your organization's readiness for AI-powered software development. Get actionable insights and a detailed roadmap for AI transformation.

Eschnou @eschnou.com · 05/06/2025

AGI or not, meaning of not, if it can (or if management decides it can) displace a large part of the workforce, it seems to me important enough to warrant a societal debate on what we do about it.

100

Eschnou @eschnou.com · 05/06/2025

What if it isn't? What if the impact is real (I believe it, I'm impacted). Shouldn't we discuss how society as a whole benefits from AI and not just a handful billionaire getting richer on the back of everyone else? We are frogs in boiling water and will realize too late what we let happen.

100

Eschnou @eschnou.com · 30/05/2025

How are you so sure? We are already seeing the effects in the creative, consulting, and software industries. At my level, I'm 5~8x productive at writing code. I don't see the new jobs coming at the same rate. Seems sensible to me to approach this with caution and ask the hard questions.

000

Reposted by Eschnou

mr. TIM @timkellogg.me · 11/04/2025

Do I know any AI engineers that have experience training LoRAs and might be looking for work? Preference for Europe/Africa time zones (DM me)

078

Eschnou @eschnou.com · 10/04/2025

The one to watch is not the cat, but the 30Y treasury. Spiking again. Getting dangerously close to 5%. The King played the (Sorcerer) Apprentice but is losing control of the spell. What if the chain reaction can't be stopped anymore? Once broken, trust is so hard to rebuild. 🎬📈🍿

3203

I'm building/experimenting with such an architecture in this project: github.com/eschnou/Open... The most amazing bit is seeing the agent react to an error (e.g. a failed web search) and finding other means to achieve its goal.

On the open source side, I had really good results with qwen-2.5-30b. I think however that you need more than a model. You still need a proper Agentic architecture, where things like chain-of-thought, ReAct, memory, tool use, etc.. remains external to the model.

Which is not a surprise since it was the stated goal from the start: depreciating the USD to make it more competitive. The challenge is to do this while keeping its status as a reserve currency and not blowing up everything. At least that's how I understand what is going on.

100

One thing to understand is that all these countries with trade surplus (in $) were recycling that surplus by buying bonds and stocks from the US. With tariffs, less trade, less surplus, less buyers, thus risks of popping the USD bubble.

100

Thanks @timkellogg.me 🙏 - MCP truly shines in these local integrations 👌

/cc @timkellogg.me - more MCP stuff for you 😅

000

GitHub - eschnou/gepetto: A minimalistic cli-based Operator

This is MIT license. So, please check it out on Github (github.com/eschnou/gepe...) and ping me if any issues or ideas for use cases to explore. Thanks!

github.com

A minimalistic cli-based Operator. Contribute to eschnou/gepetto development by creating an account on GitHub.

100

I've tested it using open-source LLM. It works great with qwen-2.5-30b which is fantastic at tool use and smart enough to keep progressing in the task. Running it on a small instance with Ollama or a provider like @groq.com or @scaleway.com

100

For browser operation, it uses Playwright in headless/accessibility mode. This allows for fast navigation and action. It doesn't support yet visual mode (which is heavier and requires multimodal models) but this is on the roadmap. Thanks @playwright.dev for the great work on the MCP connector 👌

100

At the core, this is a Agentic loop (chain-of-thoutght/ReAct/Tool use) with MCP integration. Written in Java, using Spring AI and Java MCP (thanks @tzolov.bsky.social and @thomasvitale.com 🙏) Highly extensible, works with all popular commercial and open-source LLMs

210

Gepetto - AI Browser Operator

Today I'm launching Gepetto (gepetto.sh): a cli-based AI operator to automate QA/DevOps/Data tasks using natural language. I've built this mainly for myself to automate the QA of my vibecoded projects 😅 But it could be used for so much more, let me tell you... 🧵👇 #ai #mcp #agents #operator

gepetto.sh

A minimalistic CLI-based AI agent that uses its own browser to perform tasks for you.

141

Eschnou @eschnou.com · 07/04/2025

N'est ce pas plutôt Israel == USA et dans la situation actuelle on a pas intérêt à les énerver encore plus ? La situation est catastrophique.

100

Eschnou @eschnou.com · 26/03/2025

Busy integrating MCP into opengpa.org and it is so much fun to use 🤩 Here I'm automating a QA task for wonderpod.ai using @playwright.dev and the native email integration. What's your favorite MCP server I should try to validate my integration? #mcp #ai #agentic

Of course... je suis nostalgique d'une époque où l'on avait ce genre de discussions en direct, en publique, avec un membre de cabinet de ministre... sur ce bon vieux twitter 🤷

000

Athénée ou libre ? Si c'est un Athénée, tu peux m'envoyer la grille en MP ? Clairement ici plus possible et ils renvoient à la FWB. Une grille où ceux qui ont prépa ingé n'ont pas de L2, et ceux qui ont prépa médecine ont math faible, je reste perplexe...

100

Ha ! Merci pour cette recherche. Je retrouve les même chiffres. Mais difficile de trouver une documentation de la marge de manoeuvre de l'école (e.g. 4 ou 5h de Français, 2 ou 3h de gym, etc..).

000

Ici c'est un Athénée. Donc officiel. D'après l'école ils ne peuvent plus offrir l'ancienne grille suite aux contraintes FWB sur le volume horaire. Mais je ne trouve pas la source officielle de ces règles. Perdu dans un labyrinthe de directives 😅

Je viens de trouver le rapport. Assez long mais semble bien documenté. A creuser. www.anses.fr/fr/system/fi...

anses.fr

020

C'est assez dingue comme chiffres, ils annoncent une dose journalière de 2mg/jour (personne 100kg). Je ne trouve pas le moindre article/étude pour valider ces données. Les guidelines FDA sont de 50mg. Toutes les études que j'ai trouvé (pubmed) vont vers ces chiffres.

D'après l'école, un changement des règles FWB sur le nombre maximum d'heures. C'est justement ce point que j'aimerais comprendre/valider. Mais pas certain que @valerieglatigny.bsky.social ou des membres de son staff ne soit actif sur bluesky 😔

100

Eschnou @eschnou.com · 24/03/2025

Pourtant, c'est nouveau. Voici la grille de l'année passée, qui n'a jamais posé le moindre problème à mon ado, avec math/science/L2/PES. J'ai eu un parcours similaire; comme des milliers d'étudiants. Ingé sans l'anglais ou médecin sans maths semble une aberration.

000

Vous en pensez quoi de ce nivellement par le bas ? Avec qui en discuter ici sur bluesky ? Merci 🙏 @mathieuvv.bsky.social @mariusgilbert.bsky.social @yvescoppieters.bsky.social @valerieglatigny.bsky.social

100

Eschnou @eschnou.com · 24/03/2025

J'hallucine... En Wallonie en 2025... On estime qu'un ingénieur n'est pas capable d'apprendre deux langues (EN/NL) et qu'un médecin n'est pas matheux (pas de math-fortes pour lui). Il n'est plus possible de combiner math/science/langues et prepa exam entrée pour une raison de quota d'heures.

Il s'agit de la grille d'option troisième cycle d'un Athénée. Il semble que suite à une règle FWB sur le nombre d'heures, impossible de combiner math/science/L2. L'école nous répond que ce n'est pas leur choix mais une obligation.

410

Eschnou @eschnou.com · 20/03/2025

Business idea for my US friends: laptop and smart phone rental for travelers. So you can cross the border naked without risks of being searched and blocked for something you wrote online 😅 #satire #crazytimes

000

Eschnou @eschnou.com · 17/03/2025

Tiens, la coupe du monde 2026... elle est pas organisée conjointement par USA, Mexico et Canada ? Ça promet 🤣🤦

Eschnou @eschnou.com · 15/03/2025

Cela le rappele une discussion que l'on a eu lors d'un Intermédia en 2009. J'étais jeune et naïf 😅 Je me demande si il en existe une archive, plein de choses à révisiter.

Jeff (Hot Type) Jarvis @jeffjarvis.bsky.social · 11/03/2025

Reposted by Eschnou

In its continuing good reporting on the US (vs our broken press), @zeit.de finds a paper that aligns with Trump's actions, and a supposed "Mar-a-Lago Accord (accord with whom? Trump et al). Zeit warns it could collapse the world economy. www.zeit.de/wirtschaft/2...

zeit.de

Donald Trump: Von wegen Willkür

Donald Trump und sein Team wollen mit dem Mar-a-Lago Accord das globale Handels- und Finanzsystem neu ordnen. Der Plan könnte die Weltwirtschaft abstürzen lassen.

58537

Eschnou @eschnou.com · 10/03/2025

Over the last weeks, I became a fan of @ezrakleinbot.bsky.social - insightful critical thinking of the current US situation. This latest piece has also profound parallels with Europe. We need to fix Europe so it works *for* the people, to enable build/growth/innovation instead of blocking it.

000

Eschnou @eschnou.com · 19/02/2025

I don't see the China alignment, where did you get that vibe from? It seems to me the opposite: befriending Russia to pull it away from China, while crushing Europe. EU, on the other hand, might see value in a stronger alliance with China. What do you think ?

050

Eschnou @eschnou.com · 17/02/2025

Woaw... @ezrakleinbot.bsky.social from @nytimes.com brings such fresh and hopeful coverage of the US chaos. A new podcast in my playlist 🤩 - His interview of @karaswisher.bsky.social on "the Radicalization of Elon Musk" is eye-opening. Seems a lot more good content on his channel.

100

Eschnou @eschnou.com · 09/02/2025

Toi aussi tu passes ton dimanche matin derrière le live du @vendeeglobe.bsky.social pour suivre l'arrivée de Violette ? Une des plus belles histoires sportives de ce début d'année.

Eschnou @eschnou.com · 06/02/2025

"What happened here was the gradual habituation of the people, little by little, to being governed by surprise;" This account of the gradual transformation of Germany to authoritarianism is a must-read given how similar the situation is today in the US. press.uchicago.edu/Misc/Chicago...

"You see," my colleague went on, "one doesn’t see exactly where or how to move. Believe me, this is true. Each act, each occasion, is worse than the last, but only a little worse. You wait for the next and the next. You wait for one great shocking occasion, thinking that others, when such a shock comes, will join with you in resisting somehow. You don’t want to act, or even talk, alone; you don’t want to ‘go out of your way to make trouble.’ Why not?—Well, you are not in the habit of doing it. And it is not just fear, fear of standing alone, that restrains you; it is also genuine uncertainty.

000

Je pense (et j'espère) que tout CISO/CEO/CTO se pose la question de l'état de son DRP et anticipe un acte un peu fou du genre le shutdown de Azure ou AWS. Le risque d'escalade est non-nul. Malheureusement peu/pas d'alternatives en Europe.

031

Heuh.. avant d'avancer sur les lignes rouges, merci de vérifier que begov et nos pépites du BEL20 ont les backups des data que l'on a eu la mauvaise idée de stocker sur Azure 😂🤦

131

I dunno what is the most scary: Musk team patching payment system code or teenagers deploying directly to PROD 😂🤦 talkingpointsmemo.com/edblog/musk-...

011