CTO of : 🇫🇷 https://xitter.cf/t.co/L7SpNgtyDS 🇫🇷 https://xitter.cf/t.co/eqDSbIkG9y Failed ❌ https://xitter.cf/t.co/diWCZIUMuY ❌ https://xitter.cf/t.co/OyZcyvXssv

Guangzhou, China 🇨🇳
Joined July 2014
Bryan Par retweeted
Replying to @KrzakalaF
Au contraire. C'est une nouvelle ère qui s'ouvre pour les mathématiques. Une ère où la démonstration formelle est largement automatisée et où l'accent sera reporté sur le développement de nouveaux concepts, nouvelles abstractions, nouvelles définitions, et nouvelles conjectures. L'invention du bateau a réduit l'importance de la nage, mais a permis la découverte de nouvelles terres.
145
641
142
4,508
245,004
Kind of crazy to have an AI working on 5 branches and several sub-agents, at the same time We really became x100 engineers
34
Tout seul on vite, à plusieurs on va loin Et quand le « à plusieurs » contient ton meilleur pote, c’est très très loin !
Il y a 8 ans, j'ai fait une courte "carrière" de 2 ans sur @udemy en faisant des formations sur le design et le développement web. À l'époque, j'avais même co-créé des formations avec @bryanpar_ (cf. un extrait vidéo. Jugez-moi, c'était il y a très longtemps 🤣). On a ensuite lancé une chaine Youtube ensemble "Dev Theory" sur le développement JavaScript (que Bryan à Bryan seul pendant quelques années). Et après toutes ces années, j'avais très envie de re-travailler ensemble. Puis sur un heureux hasard, on trouve l'idée de créer FlashFiscal.com en s'associant ensemble 💪 Je suis hyper fier de ce projet et de toutes les évolutions qu'on a prévu de proposer ! C'est un bonheur de pouvoir travailler avec ses meilleurs amis 🙏
4
106
The developers are not the only ones who are gonna lose their jobs to AI, biologists too 🙌
Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR. We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use. Read more: anthropic.com/news/claude-di…
1
1
90
I'm kidding, I believe in that : xitter.cf/shl/status/21023535093…
A software engineer is now a 100x engineer A non-engineer is now a 1x engineer
37
I'm a simple man. - Danny Postma creates a course - I buy
"Build me a landing page." That's how you get the same AI slop as everyone else. I'm making a landing page course for you and your AI agent to solve that ⚡ It hurts seeing good indie products launch with pages that don't do them justice. I've spent years testing pages for clients and building them for my startups. But I never made a course about this. I could teach you my process, but you'd still need years of copy and design skills to use it. Now your agent can help you do both. It just needs the right tools. I teach you why each step matters, from customer research to final design. Your agent applies it to your product. You'll learn to build high-converting landing pages that sell. 💰 Pre-orders just opened at $29. Access end of Q4. Price goes up every 200 purchases. P.S. All proceeds go toward my wife's dream cafe ☕
1
1
12
2,400
Bryan Par retweeted
A software engineer is now a 100x engineer A non-engineer is now a 1x engineer
210
333
65
6,726
271,157
Bryan Par retweeted
this is my 9/11
139
241
74
4,041
172,393
Bryan Par retweeted
Tactical programming is dead Strategic programming has never been more vital
If you're lamenting writing code by hand like something you love is being taken away from you, see if you can fall in love with solving problems instead. Maybe you'll find out that's what you really loved the whole time ❤️
56
77
8
1,509
144,663
Europe can have an amazing next few decades. I hope we can play a small role in making that more likely.
An announcement: Under the leadership of Mario Draghi and @patrickc we have set up the Rhine Group: policymakers, economists, entrepreneurs and business people pushing European reforms and the Draghi agenda. rhinegroup.eu/
166
257
42
3,522
375,176
Bryan Par retweeted
Incroyable
J'en ai profité pour recalculer l'évolution de la dette publique de la France en supposant que nous avions consacré la même fraction de la richesse nationale aux pensions que les allemands depuis 1995.
8
46
1
379
21,222
Petit imprévu : un participant ne pourra malheureusement plus être présent à prochaine La Bulle. Du coup, 1 place se libère. Comme toujours, je préfère la proposer ici pour ceux qui me suivent. 📍 Dans un Chateau près de Bordeaux 📅 Du 9 au 12 octobre 2026 Si tu veux passer 4 jours avec une quinzaine d'entrepreneurs et investisseurs pour échanger, brainstormer et créer des liens : 👉 book.stripe.com/bJecN65vB9b8… Premier arrivé, premier servi. Si tu veux savoir si c'est fait pour toi, envoie-moi un DM :)
1
1
1
4,307
Trying more seriously to use the cloud version of Codex/Agents 1) Launching all the task in the first pomodoro 2) Only checking them in the second pomodoro, never before
65
I'm now gonna try only two types of work with AI agents : 1) Full Delegation: for a big feature where I use a frontier model, and I check the result only at the next pomodoro session 2) Pairing Mode: for easy tasks with a fast AI model (like Composer) where I wait 1 minute max
I have an agent on a 15min-task, so I go to another codebase to launch another agent. Then I'm waiting for two agents, so I launch another agent on a third codebase. Now I don't have any more codebases, so I just wait?
1
73
The in-between use of an AI agent is the worst thing; waiting 10 to 20 minutes with several agents on several projects is just too much context switching to still be lucid after some hours.
36
Bryan Par retweeted
what a time to be alive
27
69
4
3,859
227,723
Febreze keeps appearing in the business books I'm reading! It’s already the second time I see a book talking about how they succeeded. 1st time was in "The Power of Habit", about how they added a nice smell to the product to create the “completion” feeling of the habit loop.
1
52
2nd time is in "Playing to Win", which I’m currently reading, about how they entered a market with a lot of competition. Interesting stories!
24
The skill "Thermo-Nuclear Code Quality Review" is a must-have for any big feature developed by an AI It really makes your codebase stronger for other big features afterward ✅
1
45