260318 x (5개) — 2026-03-18 filtered-ideas c2ea9b
[7/10] RT by @hwchase17: A couple weekends ago I attended the @sotalikesfuture x @ARIA_
RT by @hwchase17: A couple weekends ago I attended the @sotalikesfuture x @ARIA_research hackathon.
Challenge 1: build a trustworthy multi-agent network. Agents that can identify each other, prove wh
A couple weekends ago I attended the @sotalikesfuture x @ARIA_research hackathon.
Challenge 1: build a trustworthy multi-agent network. Agents that can identify each other, prove who sent what, delegate tasks with limits, and reject anything outside the trusted network.
The challenge mapped almost perfectly to what we'd been building at Kanoniv. Identity and trust for AI agents. The hackathon didn't inspire the idea, it confirmed the ecosystem needs it now.
So we shipped it.
Today we're open-sourcing kanoniv-agent-auth.
Every agent gets its own identity and keypair. Agents can delegate tasks to sub-agents with scope and budget caps, and authority narrows at each level, never widens. Every tool call is signed and verified before it executes. Revoke an agent's access and it takes effect immediately, no unwinding. Full audit trail on every action. Who did what, who authorized it, how deep in the chain.
Rust, TypeScript, Python. Same behavior across all three. MIT licensed.
github.com/kanoniv/agent-aut…
Shoutout to @ObadiaAlex and the team for organizing. The challenge was exactly the right question at the right time.
If you're building with agents that call tools, spend money, or talk to other agents, try it, tell me what breaks.
출처: https://nitter.net/sotalikesfuture"
점수: 7/10 — 점수 7/10: multi-agent
[6/10] R to @AnthropicAI: We’re now separating the safety commitments we’ll make unilat
R to @AnthropicAI: We’re now separating the safety commitments we’ll make unilaterally and our recommendations for the industry.
We’re also committing to publish new Frontier Safety Roadmaps with de
We’re now separating the safety commitments we’ll make unilaterally and our recommendations for the industry.
We’re also committing to publish new Frontier Safety Roadmaps with detailed safety goals, and Risk Reports that quantify risk across all our deployed models.
점수: 6/10 — 점수 6/10: anthropic
[9/10] RT by @hwchase17: LangChain just open-sourced a replica of Claude Code. It's cal
RT by @hwchase17: LangChain just open-sourced a replica of Claude Code. It's called Deep Agents.
MIT licensed, model-agnostic, and fully inspectable - so you can finally see exactly how coding agents
LangChain just open-sourced a replica of Claude Code. It's called Deep Agents.
MIT licensed, model-agnostic, and fully inspectable - so you can finally see exactly how coding agents like Claude Code are built under the hood.
The black box just became a textbook.
GitHub: github.com/langchain-ai/deep…
agent_orchestration claude code agent
출처: http://github.com/langchain-ai/deepagents">github.com/langchain-ai/deep…
점수: 9/10 — 점수 9/10: claude code, claude
[8/10] RT by @hwchase17: The biggest software bet Jensen made today: NemoClaw. He call
RT by @hwchase17: The biggest software bet Jensen made today: NemoClaw.
He called OpenClaw "the most popular open source project in the history of humanity."
Nvidia just made it enterprise-ready.
O
The biggest software bet Jensen made today: NemoClaw.
He called OpenClaw "the most popular open source project in the history of humanity."
Nvidia just made it enterprise-ready.
One command. Installs the full secure stack. Deploys an AI agent on your own hardware.
Jensen compared NemoClaw to what Windows did for personal computers.
Video
Shruti (@heyshrutimishra)
In collaboration with NVIDIA, I am giving away:
→ $100 BrevCode credits (1 winner)
→ NVIDIA swag T-shirts (multiple winners)
Register for GTC (free): nvda.ws/3ONqdE5
Reply with your registration screenshot + session that you are attending within next 3 days.
All the best! 😁
#NVIDIA #GTC2026 @nvidia @NVIDIAGTC
agent_orchestration agent openclaw
출처: https://nitter.net/heyshrutimishra/status/2033805372104888424#m">
점수: 8/10 — 점수 8/10: openclaw
[6/10] We hosted an executive dinner at NVIDIA GTC with @Modular. 600+ people signed u
We hosted an executive dinner at NVIDIA GTC with @Modular.
600+ people signed up, and we had to turn away more than 500. We had a packed house 🔥
This is one of the only dinners where we discuss the
We hosted an executive dinner at NVIDIA GTC with @Modular.
600+ people signed up, and we had to turn away more than 500. We had a packed house 🔥
This is one of the only dinners where we discuss the impact of AI agents across the entire stack - from infrastructure/systems to context and agentic engineering. Some of the topics we discussed:
- Is the future composed of general models or specialized models?
- Are agents a systems problem or model problem?
- How are non-technical users adopting agent tooling like Claude Cowork?
- Where do humans spend the most time on repetitive document work?
Massive thank you to the Modular team for partnering with @llama_index on this, and to every single person who showed up.
To the 500+ on the waitlist - next time we're getting a bigger venue.
agent_orchestration agent
출처: https://nitter.net/Modular"
점수: 6/10 — 점수 6/10: claude