Claude IA

Introducing Kai: My Personalized Claude Code

🤖 He's from the distant future and genderless, but I mostly refer to him as a him. I've named my entire personalized system Kai. Kai isn't a different AI model or a fork of Claude Code. Kai IS Claude Code—but completely personalized for me. Think of it this way: Claude Code is like macOS or Linux—incredibly powerful out of the box. But just like you customize your operating system with YOUR apps, YOUR shortcuts, YOUR workflows, Kai is Claude Code customized with MY knowledge, MY processes, MY d

The Skills System: The Foundation of Personalization

🎯 This is THE MOST IMPORTANT part of the entire system. If you take away one thing from this entire post, let it be this: Skills are how you transform Claude Code from a general-purpose assistant into YOUR domain expert. You don't need to fine-tune models. You need to build Skills.

How to Build Your Own Skills

Creating a skill is straightforward: Create the directory structure:~/.claude/Skills/YourSkill/ ├── SKILL.md # Routing and domain knowledge ├── Workflows/ # Step-by-step procedures └── Tools/ # CLI scripts1234Define when to use it in SKILL.md:markdown--- name: YourSkill description: What it does. USE WHEN [trigger phrases] ---1234Create workflows for common operationsBuild CLI tools for deterministic tasksDocument with examples That's it. Now Claude Code knows YOUR

What Is Personal AI Infrastructure?

So the umbrella of everything I'm gonna talk about today is what I call a Personal AI Infrastructure (PAI), which is PAI for an acronym. Everyone likes pie. It's also one syllable, which I think is an advantage. But here's what makes PAI v2 different from what came before: This isn't just a collection of prompts and tools anymore. PAI v2 is about taking Claude Code—which is already incredible—and personalizing it into YOUR cognitive operating system. Think of Claude Code as the foundation, like

Personalization > Prompting

The best prompt engineering is building a system that doesn't need perfect prompts. Everyone's obsessed with prompt engineering. "How do I write the perfect prompt?" "What's the magic phrase that makes GPT-4 work better?" The real power is in building a system that gives YOUR AI the context, tools, and structure to understand what you actually want, even when your prompts are messy. Instead of spending 20 minutes crafting the perfect research prompt every time, you build a Research skill once th

How It Actually Works

📁 Context lives in Skills, not a separate directory. Context isn't stored in a separate "context" directory anymore. Context IS the Skills. Each Skill contains its own knowledge files: ~/.claude/Skills/Blogging/ → Blog writing standards, style guides~/.claude/Skills/Research/ → Research methodology files~/.claude/Skills/Art/ → Visual aesthetic guidelines All Skills are pre-loaded into Claude Code's system prompt at startup. When you make a request, the routing system matches it to the appropria

The Hook System: Event-Driven Automation

🪝 Hooks are the nervous system—they connect everything automatically. We've covered Skills (WHAT to do), Context (WHAT to know), and History (WHAT to remember). Now let's talk about WHEN things happen automatically. The Hook System makes your personalized Claude Code reactive.

Real Examples

SessionStart Hook (~/.claude/hooks/session-start/): typescript// When session starts: // 1. Load CORE context (identity, principles, contacts) // 2. Check for active tasks from previous sessions // 3. Initialize observability tracking // 4. Set up voice server connection12345 Every time you start Claude Code, this runs automatically. You don't ask for it. It just happens. Stop Hook (~/.claude/hooks/stop/): typescript// When session ends: // 1. Extract 🎯 COMPLETED message from final response //

The Kai CLI: Voice-Enabled Claude Code

Kai est un outil CLI personnalisé qui intègre Claude Code avec des notifications vocales et une gestion de contexte. Il permet d'exécuter des requêtes en mode interactif ou ponctuel, avec support du silence et de l'intégration terminale. L'implémentation en TypeScript/Bun crée une boucle de rétroaction naturelle transformant le travail asynchrone en conscience ambiante.

Step 6: Connect to your AI assistant

json{ "mcpServers": { "website-analyzer": { "url": "https://mcp-website-analyzer.YOUR-SUBDOMAIN.workers.dev", "description": "Analyzes websites and extracts key information" } } }12345678

Testing the connection

Once connected, you can ask your AI assistant to: "Use httpx to check what technology stack danielmiessler.com uses""Scan these domains for me: example.com, test.com""What security headers does github.com have?" The AI will automatically use the MCP server tools to fetch this information.

Peut-on savoir si une IA est consciente ?

Dario Amodei est très clair : aujourd’hui, la science ne dispose d’aucun outil fiable permettant de déterminer si un système d’IA est conscient, ni même de définir précisément ce que serait la conscience dans le cas d’une machine. Il ne dit pas que les modèles actuels sont conscients.Il ne dit pas non plus qu’ils le deviendront forcément. Mais il insiste sur un point : l’absence de certitude ne permet pas d’écarter totalement la question, surtout à mesure que les systèmes gagnent en complexité,

Apple et les interfaces homme-machine

Apple poursuit sa stratégie historique en rendant les technologies numériques accessibles et ergonomiques, notamment via une commande vocale chuchotée innovante. L'assistant Siri accuse actuellement un retard face aux assistants dopés à l'IA générative, mais Apple prépare une refonte majeure en intégrant des modèles d'IA avancés, notamment via un partenariat avec Google sur Gemini. Cette combinaison devrait permettre à Apple de retrouver son avantage compétitif sur le terrain de l'interface homme-machine.

Un modèle statistique, pas un LLM

Le modèle utilisé est présenté comme statistique (arbre de décision), il ne s’agit donc pas d’IA générative (LLM). Parmi les 26 critères, on trouve l’historique des cessations, le délai d’inscription, le nombre d’entretiens, le niveau de formation, le métier recherché, l’indicateur de tension sur ce métier, les heures travaillées, la présence et l’ancienneté d’une ORE (Offre Raisonnable d’Emploi), le nombre de refus d’offres, la présence et l’ancienneté d’un CV visible, ou encore le nombre d’abs

LLMs and Automation

Overall, there is too much data in engagement logs for anyone to manually review, causing a bottleneck for analysis. To combat this issue, Janus produces normalized JSON for every task and result, making operational data usable by LLMs. Users should ensure any data shared with LLM services aligns with their organization’s data handling policies. For sensitive environments, this can be done using self-hosted models or hosted options such as Amazon Bedrock. Instead of digging through logs, teams c

The System Prompt

Before rappelling into the depths of application code, it is beneficial to provide Claude Code with contextual information for the target application and guidance on what we want to see in a response. This will result in fewer false positives and more useful responses compared to just telling Claude to “Find vulns in this app plz”. A system prompt is the perfect place to supply this. When working with an LLM, the client application maintains a rolling, limited “memory” of your conversation, call

Executive summary

An MDR alert recently led our team to an exposed server that was doing more than hosting payloads. It was functioning as a fully operational malware delivery lab. Containing over 1,000 artifacts, the infrastructure served as a QA hub where attackers systematically tested delivery paths, social engineering lures, and WebDAV execution methods. Our analysis reveals an interesting shift in adversary operations: attackers are adopting generative AI to move beyond individual exploits and operate like

Qwen 3.8, Code Kimi CLI, Netflix, pile LLM

TLDR Data20 juil.

Les API réduisent les barrières à l’entrée… ou pas

Dans la lignée d'un avis axé essentiellement sur l'amont de la chaîne de l'IA générative, l'autorité s'intéresse aux chatbots.

Bogue de facturation AWS, Codex réinitialise le tracker, LLM servant à Netflix

TLDR Data20 juil.

Meta Anthropic deal, SpaceX Pentagone calcule, migration de code AI

TLDR Data20 juil.

Observation

AI-powered browsers and assistants are designed to read and act on web content on a user’s behalf. This creates a broader attack surface for prompt injection, where malicious instructions are embedded in otherwise normal content (for example, a calendar invite, email, or document). We’ve reviewed an attack scenario that demonstrates how an AI assistant can be influenced by untrusted content to navigate the web and attempt actions a user could perform at the keyboard. If the 1Password browser ext

Who may be affected

You may be affected if all of the following apply: You use an AI-powered browser or AI assistant that can autonomously navigate and interact with web pages.The AI assistant is able to read or act on untrusted content that comes from outside your direct control, such as emails, calendar invitations, shared documents, or web pages.Your 1Password browser extension is unlocked while the AI assistant is in use.

IA générative et massification des contrôles

France Travail déploie actuellement des robots visant à automatiser et massifier le contrôle des personnes inscrites à France Travail. Depuis le 1 janvier 2025, cela inclut également les personnes au RSA. Il s'agit d'une nouvelle étape du dangereux projet de gestion algorithmique des personnes sans-