AI co-mathematicians will not be built by making one prover cleverer. They will be built by making long proofs survive time. A new paper by Yuanhe Zhang, Yuekai Sun, Taiji Suzuki, Jason D. Lee, and Fanghui Liu introduces LeanMarathon: LeanMarathon: Toward Reliable AI
SOFTWARE
-
Open-source collection of 50+ hands-on AI engineering tutorials
By
–
Hands on AI Engineering! I open-sourced a collection of 50+ hands-on AI engineering tutorials. It features step-by-step projects and tutorials on: • AI Agents and Multi-agents
• RAG (Agentic, Vision, and Local)
• MCP AI Agents
• OCR Apps
• Voice AI Agents
• & so much -
Upcoming Claude Mythos 5 release expected to surpass Opus
By
–
Holy, release is so close. It will be named „Claude Mythos 5“, a tier above Opus. I got the feeling coming week will be so huge
-
New Claude Mythos 5 Model Slug Spotted; New Model Class Coming?
By
–
BREAKING : A new Claude Mythos 5 model slug has been spotted via Dev Mode. Claude Mythos is planned to be released as its own model class, besides Haiku, Sonnet and Opus model families. Soon?
-
Perplexity surpasses a paid analyst thanks to 6 prompts
By
–
Perplexity can out-research a paid analyst.
Most people only ever use a fraction of what it does.
These 6 prompts get the rest of it, and every answer comes back with sources: -
New AI Engineering Philosophy Transforms Codebase Development, Fights System Decay
By
–
A new AI engineering philosophy flips how every codebase gets built. Most codebases get harder to work with every year. Each new feature is a negotiation with the old ones. Teams end up fighting their system instead of building on it. Every just open-sourced a plugin that
-
Building a 4-agent software team managed from Telegram and Kanban
By
–
i just built a 4-agent software team.
— Akshay 🚀 (@akshay_pachaar) 6 juin 2026
everything runs from Telegram and gets managed on a kanban board.
a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right… https://t.co/zjXOHytKHC pic.twitter.com/k3vScpYgV8i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right
-
Automate AI Agent Development Lifecycle with Antigravity 2.0
By
–
Automate your Agent Development Life Cycle using Antigravity 2.0 and Gemini Enterprise Agent Platform.
— Shubham Saboo (@Saboo_Shubham_) 6 juin 2026
Build, Evaluate and Deploy AI Agents without even leaving Antigravity.
This is the WAY. https://t.co/V8hU0dygxC pic.twitter.com/xARU2aezlyAutomate your Agent Development Life Cycle using Antigravity 2.0 and Gemini Enterprise Agent Platform. Build, Evaluate and Deploy AI Agents without even leaving Antigravity. This is the WAY.
-
Kernels Are the Actual Work in Model Inference
By
–
You don’t “run a model”
You run Kernels The model is just a graph The Inference Engine is scheduler / optimizer / executor But the actual work? That happens in the Kernels – MatMul Kernels
– Attention Kernels
– RMSNorm Kernels
– KV cache Kernels
– Quantized linear Kernels
–