New agents benchmark: CollaborativeAgentBench is the first benchmark studying collaborative LLM agents that work with humans across multi-turn collaboration on realistic tasks in backend programming & frontend design
CODE
-
PyTorch F.pad Tensor Padding API Design Discussion
By
–
lol, I think I helped design it, and I think it looks clowntown from the lens of Tensor padding. F.pad was written as a consolidation of all the vision padding — for padding images, videos, etc. It consolidated nn.ReflectionPad2d, etc. from torch7. But looking at it from the
-
Engineering at Anthropic: Developer Hub for Claude Optimization
By
–
This is our latest post in our new blog: Engineering at Anthropic. We've created this hub for developers to find practical advice and our latest discoveries on how to get the most from Claude.
-
Anthropic Launches Engineering Blog for Claude Developers
By
–
We’re launching a new blog: Engineering at Anthropic. A hub where developers can find practical advice and our latest discoveries on how to get the most from Claude.
-
Claude’s Think Tool Advances Agentic Capabilities Remarkably
By
–
The latest post is about a new method, the “think” tool, that can result in remarkable improvements in Claude’s agentic tool use ability:
-
LangSmith: Creating Datasets from Production Traces
By
–
one of the things we try to emphasize with langsmith is having different connectivity points to really get the data flywheel turning this is one of them! how to create datasets from production traces manually, automatically – we have it all!
-
Managing Long Context: Practical Tools and Solutions
By
–
we get a lot of questions about managing long context some utils here that should help with that!
-
MCP Integration for Ableton Music Production Announced
By
–
MCP for Ableton, this shit doesn’t stop
— Linus ✦ Ekenstam (@LinusEkenstam) 21 mars 2025
pic.twitter.com/QFIP9diD7xMCP for Ableton, this shit doesn’t stop
-
Kudos to sidahuj for creating MCPs and developer tools
By
–
Massive kudos to @sidahuj for making this and many other MCP’s
-
Groq Bounty Contest: Submit Your WLTS Whisper Demo Tonight
By
–
Bounty Contest submissions due tonight at midnight! Enter your demo showing how you're using WLTS with Whisper models powered by Groq for a chance to win $150 in Groq swag store credit, a feature in our developer newsletter, & social promotion! Submission form in comment