🌟 Emerging interfaces at the boundaries of AI agents🌟
↳ Models: Open Responses
↳ Tools: MCP
↳ Agents: A2A
↳ UI: AG-UI/A2UI
↳ Capabilities: Skills
↳ Telemetry: OTel GenAI
↳ IDEs: ACP
↳ Identity: AAuth
I'm mapping where they fit and how mature they are in my next post.
https://t.co/p4u4g5fg0J
Google ML Crash Course 这 3 门课(支持中文),可以按这个顺序学:
1️⃣ Linear Regression|80 min
从最基���的线性回归开始,理解 feature、label、weight、bias、loss function、gradient descent。
很多后面的 ML 概念,其实都能追溯到这里。
Linear Regression
2️⃣ Neural Networks|75 min
从线性模型进入神经网络。
重点理解 nodes、hidden layers、activation functions、forward pass、backpropagation,以及神经网络为什么能够学习 nonlinear patterns。
学完这门,对 Deep Learning 的基本工作方式会清晰很多。
Neural Networks
3️⃣ Production ML Systems|约 70–80 min
这一门非常适合 Software / Infrastructure Engineer。
真正的 ML 系统里,model 往往只是很小的一部分。还要处理 data collection、feature extraction、testing、serving、resource management、monitoring 等大量工程问题。
Kubernetes is promoting #KYAML - a stricter dialect of YAML designed to make Kubernetes configuration more explicit, predictable, and less prone to common YAML errors.
🔗 More details here: https://t.co/gEEQjBgBr1
#Kubernetes#YAML#DevOps#CloudNative#InfoQ
📊 Self-Service Data Analytics with Claude
Adding thousands of SQL examples barely moved Anthropic’s analytics accuracy. In about 80% of failures, a relevant query was already retrieved.
Structure, not access, was the bottleneck.
https://t.co/ZiRFxaLYJU
🛡️ The Hidden Primitive Behind Coding Agents
A verifier the agent can see shapes its behavior. It is not an independent contract.
Put acceptance checks outside the writer’s:
→ context
→ tools
→ workspace
https://t.co/DNnIYCUZ3i
We started to post videos for CMU 11-768, AI Agents!
All of the videos will be posted to this playlist, so please bookmark/follow it if you want to be notified of new ones! I'll also try to post them on this thread too.
https://t.co/HAJgKXve0x