I love this figure from Anthropic's new talk on "Skills > Agents". Here are my notes: The more skills you build, the more useful Claude Code gets. And it makes perfect sense. Procedural knowledge and continuous learning for the win! Skills essentially are the way you make

I love this figure from Anthropic's new talk on "Skills > Agents". Here are my notes: The more skills you build, the more useful Claude Code gets. And it makes perfect sense. Procedural knowledge and continuous learning for the win! Skills essentially are the way you make

I will be covering Skills in our upcoming Claude Code build sessions. There are so many impactful ways that non-technical or technical folks can build with Skills. The time to jump into this stuff is now: https://t.co/lmI57QlqVs

New research from Google: "The Illusion of Deep Learning Architecture". For those following research on continual learning, you may want to bookmark this one. Instead of stacking more layers, what if we give neural networks more levels of learning? The default approach to

Easy to give Mistral Vibe access to MCP and custom tools. It uses config.toml for setting up custom tools and custom agents as well.

It has access to tools like search, grep, bash, and a task manager for planning.

I really like the built-in theme changer. :)

https://t.co/8ikbwa39SA

Looks like Mistral has entered the agentic coding arena! They just released Mistral Vibe CLI, an open-source command-line coding assistant powered by Devstral.

The AI Consumer Index (ACE) Most AI benchmarks today focus on reasoning and coding. But most people use AI to shop, cook, and plan their weekends. In those domains, LLM hallucinations continue to be a real problem. 73% of ChatGPT messages (according a recent report) are now

Integrating LLMs with knowledge bases. Important read for AI practitioners LLMs generate impressive text but struggle with hallucinations, outdated knowledge, and reasoning over structured data. The default response has been scaling up (e.g., more parameters, more compute, more

I totally get this. However, I prefer to prompt LLMs to plan first before jumping in. When that plan is in context it leads to more effective multi-turn conversations and better intent understanding. This is why using plan mode in Claude Code is extremely effective. There are

New survey on Agentic LLMs. The survey spans three interconnected categories: reasoning and retrieval for better decision-making, action-oriented models for practical assistance, and multi-agent systems for collaboration and studying emergent social behavior. Key applications

Top AI Papers of the Week (Dec 1 - 7): - DeepSeek-V3.2 - Is Vibe Coding Safe? - Quiet Feature Learning - Autonomous Cloud Reliability - Thinking with Programming Vision - Evolving Multi-Agent Orchestration - Training LLMs for Honesty via Confessions Read on for more:

Google just published a banger guide on effective context engineering for multi-agent systems. Pay attention to this one, AI devs! (bookmark it) Here are my key takeaways: Context windows aren't the bottleneck. Context engineering is. For more complex and long-horizon

This is a really good report on the reality of building agents in production.

First large-scale study of AI agents actually running in production. The hype says agents are transforming everything. The data tells a different story. Researchers surveyed 306 practitioners and conducted 20 in-depth case studies across 26 domains. What they found challenges

Google just published a banger guide on effective context engineering for multi-agent systems. Pay attention to this one, AI devs! (bookmark it) Here are my key takeaways: Context windows aren't the bottleneck. Context engineering is. For more complex and long-horizon

// THE CASE FOR ENVIRONMENT SCALING // Environment scaling may be as important as model scaling for agentic AI. Current AI research suggests that building a powerful agentic AI model isn't just about better reasoning. It's also about better environments. The default approach

Next week, we start our first live cohort on building with Claude Code. Excited to share how I've been using Claude Code for coding, research, designing, searching, and everything in between. You also get to build. :) A few more seats are available if you are interested.