今日摘要

Hugging Face Blog:A New Framework for Evaluating Voice Agents (EVA)

Interconnects AI:The case for why self-improvement is real but it doesn't lead to fast takeoff.

OpenAI Blog:OpenAI launches a Safety Bug Bounty program to identify AI abuse and safety risks, including agentic vulnerabilities, prompt injection, and data exfiltration.

LangChain Blog:Discover how Kensho, S&P Global’s AI innovation engine, leveraged LangGraph to create its Grounding framework–a unified agentic access layer solving fragmented financial data retrieval at enterprise scale.

LangChain Blog:💡 TLDR: The best agent evals directly measure an agent behavior we care about. Here's how we source data, create metrics, and run well-scoped, targeted experiments over time to make agents more accurate and reliable. Evals shape agent behavior We’ve been curating evaluations to measure and

观点摘要:Build a Domain-Specific Embedding Model in Under a Day

观点摘要:Learn how STADLER uses ChatGPT to transform knowledge work, saving time and accelerating productivity across 650 employees.

观点摘要:A practical checklist for agent evaluation: error analysis, dataset construction, grader design, offline & online evals, and production readiness.

观点摘要:Liberate your OpenClaw

观点摘要:Friend bubbles in Facebook Reels highlight Reels your friends have liked or reacted to, helping you discover new content and making it easier to connect over shared interests. This article explains the technical architecture behind friend bubbles, including how machine learning estimates relationship strength and ranks content your friends have interacted with to create more [...] Read More... The post Friend Bubbles: Enhancing Social Discovery on Facebook Reels appeared first on Engineering at Meta .

A New Framework for Evaluating Voice Agents (EVA)

来源:Hugging Face Blog

标签:#Buildable #Workflow

原文:A New Framework for Evaluating Voice Agents (EVA)

链接:https://huggingface.co/blog/ServiceNow-AI/eva

观点:A New Framework for Evaluating Voice Agents (EVA)

Lossy self-improvement

来源:Interconnects AI

标签:#News #Agent

原文:The case for why self-improvement is real but it doesn't lead to fast takeoff.

链接:https://www.interconnects.ai/p/lossy-self-improvement

观点:The case for why self-improvement is real but it doesn't lead to fast takeoff.

Introducing the OpenAI Safety Bug Bounty program

来源:OpenAI Blog

标签:#Release #Workflow

原文:OpenAI launches a Safety Bug Bounty program to identify AI abuse and safety risks, including agentic vulnerabilities, prompt injection, and data exfiltration.

链接:https://openai.com/index/safety-bug-bounty

观点:OpenAI launches a Safety Bug Bounty program to identify AI abuse and safety risks, including agentic vulnerabilities, prompt injection, and data exfiltration.

How Kensho built a multi-agent framework with LangGraph to solve trusted financial data retrieval

来源:LangChain Blog

标签:#Buildable #Workflow

原文:Discover how Kensho, S&P Global’s AI innovation engine, leveraged LangGraph to create its Grounding framework–a unified agentic access layer solving fragmented financial data retrieval at enterprise scale.

链接:https://blog.langchain.com/customers-kensho/

观点:Discover how Kensho, S&P Global’s AI innovation engine, leveraged LangGraph to create its Grounding framework–a unified agentic access layer solving fragmented financial data retrieval at enterprise scale.

How we build evals for Deep Agents

来源:LangChain Blog

标签:#Buildable #Workflow

原文:💡 TLDR: The best agent evals directly measure an agent behavior we care about. Here's how we source data, create metrics, and run well-scoped, targeted experiments over time to make agents more accurate and reliable. Evals shape agent behavior We’ve been curating evaluations to measure and

链接:https://blog.langchain.com/how-we-build-evals-for-deep-agents/

观点:💡 TLDR: The best agent evals directly measure an agent behavior we care about. Here's how we source data, create metrics, and run well-scoped, targeted experiments over time to make agents more accurate and reliable. Evals shape agent behavior We’ve been curating evaluations to measure and

Build a Domain-Specific Embedding Model in Under a Day

来源:Hugging Face Blog

标签:#Analysis #Model

原文:Build a Domain-Specific Embedding Model in Under a Day

链接:https://huggingface.co/blog/nvidia/domain-specific-embedding-finetune

观点:Build a Domain-Specific Embedding Model in Under a Day

STADLER reshapes knowledge work at a 230-year-old company

来源:OpenAI Blog

标签:#News #Application

原文:Learn how STADLER uses ChatGPT to transform knowledge work, saving time and accelerating productivity across 650 employees.

链接:https://openai.com/index/stadler

观点:Learn how STADLER uses ChatGPT to transform knowledge work, saving time and accelerating productivity across 650 employees.

Agent Evaluation Readiness Checklist

来源:LangChain Blog

标签:#Analysis #Application

原文:A practical checklist for agent evaluation: error analysis, dataset construction, grader design, offline & online evals, and production readiness.

链接:https://blog.langchain.com/agent-evaluation-readiness-checklist/

观点:A practical checklist for agent evaluation: error analysis, dataset construction, grader design, offline & online evals, and production readiness.

Liberate your OpenClaw

来源:Hugging Face Blog

标签:#News #Agent

原文:Liberate your OpenClaw

链接:https://huggingface.co/blog/liberate-your-openclaw

观点:Liberate your OpenClaw

Friend Bubbles: Enhancing Social Discovery on Facebook Reels

来源:Meta Engineering

标签:#News #Application

原文:Friend bubbles in Facebook Reels highlight Reels your friends have liked or reacted to, helping you discover new content and making it easier to connect over shared interests. This article explains the technical architecture behind friend bubbles, including how machine learning estimates relationship strength and ranks content your friends have interacted with to create more [...] Read More... The post Friend Bubbles: Enhancing Social Discovery on Facebook Reels appeared first on Engineering at Meta .

链接:https://engineering.fb.com/2026/03/18/ml-applications/friend-bubbles-enhancing-social-discovery-on-facebook-reels/

观点:Friend bubbles in Facebook Reels highlight Reels your friends have liked or reacted to, helping you discover new content and making it easier to connect over shared interests. This article explains the technical architecture behind friend bubbles, including how machine learning estimates relationship strength and ranks content your friends have interacted with to create more [...] Read More... The post Friend Bubbles: Enhancing Social Discovery on Facebook Reels appeared first on Engineering at Meta .