I had a fantastic conversation a few months ago about WebMCP as accessibility technology I hadn't thought about it before but it feels like a great opportunity to massively increase the utility of many web apps for screen reader users under the guise of "adding support for AI"
CODE
-
Science Resources Hub: Chemistry Biology Physics Materials Math
By
–
Super happy to have this one out. A clean organized up-to-date view of all the science resources (chemistry, biology, physics, materials, math) people have been sharing on the Hugging Face hub: datasets, blogs, models and more https://t.co/3Wk2TZteAT
— Thomas Wolf (@Thom_Wolf) 29 avril 2026Super happy to have this one out. A clean organized up-to-date view of all the science resources (chemistry, biology, physics, materials, math) people have been sharing on the Hugging Face hub: datasets, blogs, models and more
-
Platform Differences in AI Implementation and Coupling
By
–
i haven't seen any write ups tbh – would want to. i've only heard about one platform tbh but it may be similar across the board, or not! v0 may be different too to be tightly coupled with vercl but also no idea haha
-
Reducing Dependencies for Better Security and Performance
By
–
sorry! We worked hard to move off many dependencies to reduce install size, time and security risk re supply chain attacks. That has some growing pains.
-
Embedding Layers in Small Models: Architecture and Training Optimization
By
–
Did you know that the embedding layer can contain 63% of total model parameters? In this talk, I present unique challenges of small models from architecture (don't build giant embedding layers) to post-training (how to fix doom looping) ↓ Slides in the comments ↓
-
AI Generation Quality Assessment Beyond Candidate Quantity
By
–
Generating candidates is now easy compared to back then. An AI can generate: 100 prompt variants 50 code changes 20 tool-routing ideas 10 eval rewrites 5 new workflows
The question is not “can it come up with changes?”
The question is “which changes are actually better?” -
Building and Deploying Agents with DeepAgents Deploy
By
–
That's a quick tour through building and deploying a simple agent with DeepAgents deploy Was just a markdown file, a json file, and toml file Easy to set up, but robust deployment by the end Try out deepagents deploy! Full docs here:
-
Agent Deployment via MCP, A2A and Remote Graph API
By
–
As part of this deployment, you can interact with the agent in several ways We expose the agent via MCP and A2A, as well as with as a "remote graph" API, which means you can interact with as you would a normal in-memory graph See streaming docs here: https://
docs.langchain.com/langsmith/stre
aming
… -
User-Friendly Agent Interaction in LangSmith Studio
By
–
Interacting with the agent in the studio is the easiest way to get a user friendly UI! I can share it with others in my LangSmith org, and they can chat with it there
-
Deploy AI Agents to LangSmith Using deepagents and Docker
By
–
After that, it's go time! `deepagents deploy` This will use Docker under the hood, so make sure you have that installed It will build an agent server image, and then deploy it to LangSmith