Belated Life Update: Finished my PhD & joined @SakanaAILabs recently! I've been working on AI Scientist-v2 and will be giving two invited talks on Sat and Mon at #ICLR2025! Looking forward to discussing AI-driven scientific discovery & LLM agents!
AGENTS
-
Perplexity Voice Assistant Launches on iOS Platform
By
–
Perplexity Voice Assistant is now on iOS. https://t.co/P2YsImozQu
— Perplexity (@perplexity_ai) 25 avril 2025Perplexity Voice Assistant is now on iOS.
-
Developer Competition: Build AI Breakthroughs and Climb Leaderboard
By
–
There's still time to engage! Connect with other devs Climb the leaderboard Earn credits + serious bragging rights Then, go create the next AI breakthrough. We’re watching. Jump in
-
Thumbnail usage credited for Hugging Face tiny agents blog
By
–
took the liberty of using this as a thumbnail for https://
huggingface.co/blog/tiny-agen
ts
… – credited you in the blogpost, hope that was ok! -
Build WhatsApp AI Agents with LangGraph Supervisor Architecture
By
–
WhatsApp Agent Template Build AI agents for WhatsApp with this comprehensive template. LangGraph's supervisor architecture enables text and image handling with enterprise-grade security and monitoring. Start building a WhatsApp AI agent today!
Repo link in reply -
Groq Desktop Beta: Fast Inference with External Tools Integration
By
–
Tired of slow MCP hosts? Try Groq Desktop Beta. You can now connect the models you love running on Groq for lightning-fast inference with the external tools and APIs you rely on for their capabilities. Speed meets functionality. Check out our new tutorial, link in the comments,
-
TINY AGENTS: 50-Line JavaScript Agent Framework
By
–
BOOOOM: Today I'm dropping TINY AGENTS the 50 lines of code Agent in Javascript I spent the last few weeks working on this, so I hope you will like it. I've been diving into MCP (Model Context Protocol) to understand what the hype was all about. It is fairly simple, but
-
Assign a thinking role to sharpen model output
By
–
First, assign the model a thinking role. This changes how it “shows up” mentally. Examples: – Strategy Consultant
– Logical Analyst
– Detective
– Policy Evaluator
– Research Synthesizer The more specific the role, the sharper the output. -
Paper2Code: Automated ML Paper to Runnable Code Framework
By
–
Paper2Code, from KAIST, is a multi-agent LLM framework that turns ML papers into runnable code repos—automatically! Bridging the gap between research and implementation, one agent at a time.
Paper: https://
arxiv.org/pdf/2504.17192 -
Google Presents Gemini Agents and Development Kits at ICLR2025
By
–
At #ICLR2025? Drop by the Google booth today at 5 PM when Zizhao Zhang will present recent research progress on Gemini for Agent for developers and enterprise, including Agent Development Kits (ADK) to let you build and deploy agents easily. https://
cloud.google.com/blog/products/
ai-machine-learning/build-and-manage-multi-system-agents-with-vertex-ai?e=4875480
…