I tested this prompt on the topic: “The Role of AI in Scientific Discovery” LLMs returned: – 5+ sub-topics
– Top cited papers
– Major debates (e.g., human vs. machine creativity)
– Knowledge gaps for future work No fluff. Just academic-grade insight.
OPEN SOURCE
-
AI in Science: Insights, Debates, and Gaps
By
–
-
Mistral Launches Mistral Code Coding Assistant with Multiple Models
By
–
Mistral just launched Mistral Code, a vibe coding assistant featuring: —Four coding models, including Devstral and Codestral
—Full-stack ownership from models and plugins, to infra under one SLA
—80+ languages, Git-awareness, terminal-integration -
Codex Co-Authors New TypeScript Agents SDK with Impressive Metrics
By
–
Codex was a key co-author of our new Agents SDK for TypeScript! 261 tasks handled, 103 PRs merged, and bugs caught early. Check out @DKundel
’s thread for all the details: -
META-AGENTIC AGI ALPHA AGENT GITHUB RELEASE
By
–
META-AGENTIC α‑AGI Out‑learn · Out‑think · Out‑design · Out‑strategise · Out‑execute GitHub : https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0
… #AGIALPHA #MetaAgentic #ASIFirst -
Killer App Ideas for Gradio Agents MCP Hackathon
By
–
Killer app ideas for the Gradio x Agents x MCP Hackathon, a 🧵 https://t.co/8Kfjtw2i0h
— Hugging Face (@huggingface) 4 juin 2025Killer app ideas for the Gradio x Agents x MCP Hackathon, a
-
FLUX Kontext Now Supports Multiple Image Inputs
By
–
We hacked FLUX Kontext to support >2 images input. It's experimental. It's fun. Try it. https://
replicate.com/flux-kontext-a
pps/multi-image-list
… -
Researcher Asked to Share Experimental Code Source
By
–
Really nice work, thanks for sharing! Out of curiosity, do you intend to release the code used for these experiments as well?
-
DSPy: Build and Optimize Agentic Apps Short Course
By
–
New short course: DSPy: Build and Optimize Agentic Apps
— Andrew Ng (@AndrewYNg) 4 juin 2025
DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with @databricks and taught by… pic.twitter.com/1KRz7XvxXeNew short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with @databricks and taught by
-
Flux-Kontext-Pro Model Surpasses Half Million Public Runs
By
–
Already over half a million runs on our public flux-kontext-pro model. Dang y'all.