Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
J'ai compilé tout ça :
17 modules, +200 exemples de code, mises à jour régulière. 89€.
De "j'utilise Claude Code" à "je maîtrise ce nouveau paradigme".
→ https://t.co/SsrvNf5PyK
La plupart des devs "utilisent" Claude Code.
Très peu le maîtrise vraiment.
La différence : 6 mois d'avance sur leurs collègues.
Voici ce qu'il y a derrière 👇
Claude Code que tu utilises déjà :
slash commands, autocomplete, refactor.
Claude Code que tu connais pas encore :
• skills → composer des comportements
• hooks → automatiser
• subagents → paralléliser
• MCP → brancher tes outils
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude.
Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
💡 Astuce Claude Code :
Arrêtez de taper les mêmes prompts en boucle.
Créez un skill (~/.claude/skills/mon-skill/SKILL.md) avec vos instructions + exemples, et Claude l'invoquera tout seul quand le contexte matche.
Un workflow répété 3 fois = un skill.
Introducing Claude Opus 4.7, our most capable Opus model yet.
It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back.
You can hand off your hardest work with less supervision.
🚀 Google vient de sortir un repo de skills Android officiel.
Compose, archi, coroutines, migration AGP 9.x ... de quoi gagner pas mal de temps quand on bosse avec un agent IA sur du code Android.
👉 https://t.co/96DFdTxRzx
#AndroidDev#AI#Kotlin#Skills
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.
https://t.co/NQ7IfEtYk7
Fuite chez Anthropic, nouveau modèle Claude confirmé :
• Nom : "Mythos" (tier "Capybara")
• Au-dessus d'Opus dans la hiérarchie
• Meilleur en coding, raisonnement, cybersécurité
• Pas de date de sortie
• Accès restreint pour l'instant
「Claude Code insights」
The default effort for a model is set to "medium".
If you want the model to think harder, use this command in claude :
`/effort high`
Announcing ARC-AGI-3
The only unsaturated agentic intelligence benchmark in the world
Humans score 100%, AI <1%
This human-AI gap demonstrates we do not yet have AGI
Most benchmarks test what models already know, ARC-AGI-3 tests how they learn
I’m excited to announce the release of ComposeGuard, a new open-source plugin for Android Studio and IntelliJ IDEA!🚀
It brings real-time Jetpack Compose best-practice checks and rule violation detection right into your editor.
https://t.co/pZ3Zdz6LGC
Today, we are releasing FineVision, a huge open-source dataset for training state-of-the-art Vision-Language Models:
> 17.3M images
> 24.3M samples
> 88.9M turns
> 9.5B answer tokens
Here are my favourite findings:
🎉 The new Kotlin Multiplatform for IntelliJ IDEA and Android Studio!
✨ Integrated New Project wizard
🔍 Preflight checks
🔧 Multiplatform run configurations
🧭 Cross-language support
🎨 Compose Multiplatform support
🔥 Compose Hot Reload
Learn more:
https://t.co/s0ugMTIST8