Cocoon β Confidential Compute Open Network
https://cocoon.org/
https://cocoon.org/
Cocoon
Confidential Compute Open Network
Cocoon connects GPU power, AI, and Telegramβs vast ecosystem β all built on privacy and blockchain.
Introducing advanced tool use on the Claude Developer Platform \ Anthropic
https://www.anthropic.com/engineering/advanced-tool-use
https://www.anthropic.com/engineering/advanced-tool-use
Anthropic
Introducing advanced tool use on the Claude Developer Platform
Claude can now discover, learn, and execute tools dynamically to enable agents that take action in the real world. Hereβs how.
Claude Skills are awesome, maybe a bigger deal than MCP
https://simonwillison.net/2025/Oct/16/claude-skills/
https://simonwillison.net/2025/Oct/16/claude-skills/
Simon Willisonβs Weblog
Claude Skills are awesome, maybe a bigger deal than MCP
Anthropic this morning introduced Claude Skills, a new pattern for making new abilities available to their models: Claude can now use Skills to improve how it performs specific tasks. Skills β¦
Effective harnesses for long-running agents \ Anthropic
https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents
https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents
Anthropic
Effective harnesses for long-running agents
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
blood doesnβt measure function, it measures the leftovers of a system fighting to keep the numbers stable
In A World Without Chatbots
https://research.humancomputerlab.com/in-a-world-without-chatbots-2/
https://research.humancomputerlab.com/in-a-world-without-chatbots-2/
[Human Computer Lab]
In A World Without Chatbots
Everyday, millions of people open ChatGPT, type their questions, and wait for text to scroll across their screen. As a researcher at [Human Computer Lab], I've watched this pattern repeat endlessly and it's made me question something fundamental: is thisβ¦
[2507.05558] AI Agent Smart Contract Exploit Generation
https://arxiv.org/abs/2507.05558
https://arxiv.org/abs/2507.05558
arXiv.org
AI Agent Smart Contract Exploit Generation
Smart contract vulnerabilities have led to billions in losses, yet finding actionable exploits remains challenging. Traditional fuzzers rely on rigid heuristics and struggle with complex attacks,...
super nice, can use it for free inbrowser sandbox for making audio for videos or audiogram
good question to ask AI which is increasingly getting smarter:
given how I think, what are the environments where my cognition gives me an unfair advantage?
given how I think, what are the environments where my cognition gives me an unfair advantage?
Claude Code + Bugster Integration - AI Test Generation
https://docs.bugster.dev/guides/coding-agents/claude-code#browser-testing-skill
https://docs.bugster.dev/guides/coding-agents/claude-code#browser-testing-skill
Bugster
Claude Code + Bugster Integration - AI Test Generation
Configure Claude Code to be your Bugster test generation assistant