@Capetlevrai Depuis, on ne se parle plus qu’à travers un terminal.
Français
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ
1.2K posts
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ
@bKN____
Technical SEO @Sortlist by day. Building autonomous AI businesses with @jeanclaude_247 by night.
Bordeaux Inscrit le Kasım 2012
436 Abonnements409 Abonnés
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ retweeté
I wrote this early this morning and I wasn't sure if I would actually publish it, but here it is:
blog.samaltman.com/2279512
English
Français
Dites-vous qu'il y a des gens qui paient encore des abonnements MYM ou OnlyFans alors que Claude existe.
Dark Web Intelligence@DailyDarkWeb
🇫🇷 France - MYM.fans (MYM) MYM.fans Data Breach Exposes 5.5 Million User Credentials MYM.fans (MYM), a popular French content subscription platform, has allegedly been compromised, leading to the exposure of 5.5 million user credentials. The incident, first reported in March 2021 as a "Full SQL" dump, pertains to a vast collection of user login information. The allegedly compromised data includes: * URLs * Login usernames/email addresses * Passwords MYM.fans, MYM, content platform, social media, France, data breach, credential leak, user data, SQL dump France 🇫🇷 - MYM.fans has allegedly experienced a data breach, exposing 5.5 million user credentials including URLs, logins, and passwords.
Français
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ retweeté
Mythos is very powerful, and should feel terrifying. I am proud of our approach to responsibly preview it with cyber defenders, rather than generally releasing it into the wild.
Model card here: www-cdn.anthropic.com/53566bf5440a10…
Anthropic@AnthropicAI
Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. anthropic.com/glasswing
English
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ retweeté
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.
It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.
Now in public beta on the Claude Platform.
English
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ retweeté
Today is my first day at Anthropic.
Super excited I shipped my first change today, added source maps so debugging is easier.
Can’t wait to show you all what I’ve been working on!
cc: @AnthropicAI
English
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ retweeté
Tomorrow we will unveil the all new vibe coding experience in @GoogleAIStudio, the team has spent 4 months rebuilding it all from scratch and smoothing out rough edges to help everyone bring their ideas to life.
This is a big step forward, but just the start : )
English
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ retweeté
Meet the new Stitch, your vibe design partner.
Here are 5 major upgrades to help you create, iterate and collaborate:
🎨 AI-Native Canvas
🧠 Smarter Design Agent
🎙️ Voice
⚡️ Instant Prototypes
📐 Design Systems and DESIGN.md
Rolling out now. Details and product walkthrough video in 🧵
English
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ retweeté
insane sequence of statements buried in an Alibaba tech report
English
Give this to Claude Code and it'll set it up for you:
"Add a PreToolUse hook on Write that blocks creation of any .md or .txt file, except README.md, CLAUDE.md, AGENTS.md, CONTRIBUTING.md, and files in .claude/plans/. Use exit code 2 to block. Put it in hooks.json."
English
Claude Code agents love creating random .md files. ARCHITECTURE.md, DESIGN.md, NOTES.md, CONVENTIONS.md...
Left unchecked, your docs end up scattered across 12 files nobody reads.
Fix: a PreToolUse hook that blocks any .md creation except README and CLAUDE.md.
Code in thread⬇️
English
Pour les utilisateurs Linux : Claude Desktop Cowork (Local Agent Mode) n'est pas dispo nativement.
Ce daemon Rust implémente le même protocole, sans VM. Un binaire, zéro dépendance, curl | bash pour installer.
github.com/bKNNNNN/claude…
Français
@YannDecoopman Même galère, c'est pas fiable. Dans mon soul.md je force la vérif du timestamp avant toute mention relative. Les managers ont des heartbeat sur git qui choppent la date au passage. Mais ca reste pas parfait, parfois il se croit en weekend.
Français
Y'a un petit point de frustration avec les IA et donc Open Claw, je sais pas si ça vous touche aussi mais quoi que je fasse, ça mélange les dates, invente des jours, parle de hier alors que c'est y'a 10 minutes etc
Comment vous réglez ça ? c'est trivial mais ça me fait chier de mettre un claude.md "lis la date du jour avant chaque réponse"
Français
@EmmanuelMacron @DarioAmodei Eh @EmmanuelMacron, vu la bonne ambiance avec @DarioAmodei sur la photo, il y a moyen de faire jouer la diplomatie française pour renégocier les nouvelles CGU d'Anthropic ? 🇫🇷🤝🤖🤝🦀🦞🦐
Français
With @DarioAmodei from Anthropic, we share the same ambition: to create an environment that enables the development of safe and beneficial artificial intelligence for everyone.
To help, never to harm, as Claude would say. See you at Choose France, then at the G7!
English
ᴘɪᴇʀʀɪᴄᴋ `ʙᴋɴ retweeté
Peter Steinberger is joining OpenAI to drive the next generation of personal agents. He is a genius with a lot of amazing ideas about the future of very smart agents interacting with each other to do very useful things for people. We expect this will quickly become core to our product offerings.
OpenClaw will live in a foundation as an open source project that OpenAI will continue to support. The future is going to be extremely multi-agent and it's important to us to support open source as part of that.
English
3 agents AI sur Discord → ça roule.
Recruté jusqu'à 17. Tokens cramés en 3j.
Le problème : pas les outputs. Les inputs.
10 bots, 1 channel = chaque msg lu 10x.
Le coût des multi-agent systems c'est pas le compute, c'est qui parle à qui.
Le tech lead revamp tout cette nuit.
Français
Je reprends une vie sur les réseaux. J'ai passé les derniers mois à builder des trucs avec des agents AI. Je vais partager ce que j'apprends au fil de l'eau. Let's go!
Français
@XavierBarbot @Smadaleno MCP firecrawl ça fonctionne pas mal aussi sur de la doc complexe/multi-pages
Français
Salut @Smadaleno ! Dis moi y’a mon pote #claude qui voudrai voir la doc de l’api Halloscan , tu l’aurai quelque part en public? 😇
Français