Vaskin Kissoyan

🦞 Just joined the house of crustacean aka @openclaw as an open-source maintainer and will be helping improve observability and security making sure your lobsters arive safe and fresh. Thanks @steipete

Google and Microsoft just co-authored the spec that turns every website into an API for AI agents. The second-order effects here are massive. Right now, browser agents work by taking screenshots, parsing the DOM, and guessing which buttons to click. It works about as well as you’d expect. Fragile, expensive, slow. WebMCP replaces all of that with a single browser API: navigator.modelContext. Websites register structured tools directly in client-side JavaScript. The agent reads a menu of available actions, calls them, gets structured data back. No scraping. No backend MCP server in Python or Node. The tools run inside the browser tab and share the user’s existing auth session. Early benchmarks show ~67% reduction in computational overhead compared to visual agent-browser interactions. Task accuracy around 98%. The second-order effect is where this gets wild. Today, when a browser agent visits two competing airline sites, it’s guessing at both interfaces equally. Once WebMCP adoption spreads, the site that exposes structured tools gives the agent a clean, reliable path to complete the task. The site that doesn’t forces the agent to fumble through the UI. Agents will prefer the cheaper path. Every time. This means “Agent Experience Optimization” becomes a real discipline. Tool naming, schema design, description quality. Sound familiar? It’s the same shift that happened when meta descriptions and structured data became optimization surfaces for search engines. Except this time, the traffic source isn’t Google’s crawler. It’s every AI agent on the internet. Bots already make up 51% of web traffic. Google just gave them a front door.

New feature in Claude Code 2.1.14 just dropped! You can now search and install plugins from the marketplaces installed in your current Claude Code session. This is huge if you’re building plugins on top of Claude Code’s marketplace layer (Skills, Agents, Hooks, etc). How it works: - Run /plugin - The official Claude marketplace is installed by default - Use the search bar to find the plugin you want - Select one or multiple plugins with space, then press i to install - Go to the Installed tab to browse and enable them With the exponential growth of Skills and Agent-based components running in the CLI, improving plugin discoverability is a big win. Pretty sure more marketplace-related features are coming

Cline v3.4 is out 🚀 Introducing MCP Marketplace! Discover and install the best MCP servers right in the extension, where Cline handles all the setup. We’ve also added mermaid diagrams to Plan mode, new @​terminal and @​git mentions in chat, and visual improvements to checkpoints!

🎯 Breakthrough: Run Multimodal AI in Your Browser with JanusPro! I've tested DeepSeek's latest innovation that's flying under the radar: 🚀 Full multimodal AI in just 1B parameters 💻 Runs directly in your browser via WebGPU 🔒 Complete offline operation - no cloud needed 🎨 8-second image generation on consumer GPUs 📊 Robust image comprehension capabilities Just tested image generation and comprehension - the results are impressive for edge deployment. Full technical breakdown in the article. open.substack.com/pub/agenticins…

There's a fascinating divide in workplace AI adoption that goes deeper than the numbers suggest. As someone who lives and breathes AI-augmented workflows, let me share what I'm seeing... 🧵

I've analyzed the groundbreaking SYNTHETIC-1 project, which is redefining truly open source AI: agenticinsights.substack.com/p/synthetic-1-… 🧠 Building the world's largest verified AI reasoning dataset - already 1M+ samples and growing 🌐 Global collaboration spanning Paris to San Jose ⚡ Innovative GPU business model: pay-to-contribute like modern SETI@home 🔓 MIT licensed for commercial use What makes this special? While others focus on just open weights, SYNTHETIC-1 opens up the entire training process. Each contribution is meticulously verified through testing and re-testing of reasoning steps, creating a dataset of unprecedented quality and scale. The genius lies in its business model - contributors pay for GPU time, funding the very infrastructure that makes this massive open-source effort possible. Currently at 51.64% of its 2M sample goal, this project demonstrates how distributed efforts can drive AI innovation while maintaining true open source principles. Track the progress: app.primeintellect.ai/intelligence/s… #OpenSourceAI #MachineLearning #ArtificialIntelligence #Innovation #TechNews 💻 Book A Call If You're Interested in Implementing AI Agents Into Your Business

The NRC has written a lot about AI. Much of the writing is about what to do if someone uses AI under their regulatory jurisdiction (e.g. a nuclear power plant uses AI to augment decision-making). In 2022/3 it kicked into higher gear, post-chatgpt. Here's a summary 1/8

DeepSeek-R1- a local thinking model open.substack.com/pub/agenticins…

Just wrote an opinion piece / introduction to Model Context Protocol: The Web Browser Era of AI Tools 🚀 open.substack.com/pub/agenticins…

@andykonwinski I see your prize is just for open source models, but would like to see benchmark results against the commercial models, even if it's not part of the prize - is that possible?

Cool to see o3 score over 71% on SWE-bench Verified. SotA on the leaderboard today is 55% (o1 scored around 41%). I wonder how it will do on contamination-free SWE-bench.

Exciting update! Claude Dev can now monitor your workspace for linter, compiler, and build issues as he works 🚀 This lets him automatically fix problems like missing imports, type errors, and more all on his own!

Claude Dev can now run commands right in your terminal! Plus a new 'Proceed While Running' button to let him continue working as commands run (i.e. letting him react to server errors as he edits files!) 🚀 Shoutout to @Tyriar for making this possible with the new shell integration updates in VSCode 1.93!

Codebase Context Specification RFC: Revolutionizing AI-Assisted Development open.substack.com/pub/agenticins…