第37期 AI News Daily｜scan-for-secrets 0.3
今日摘要
AWS Machine Learning Blog：In this post, we walk through building a custom HR onboarding agent with Quick. We show how to configure an agent that understands your organization’s processes, connects to your HR systems, and automates common tasks, such as answering new-hire questions and tracking document completion.
AWS Machine Learning Blog：In this post, we walk through how we fine-tuned Qwen 2.5 7B Instruct for tool calling using RLVR. We cover dataset preparation across three distinct agent behaviors, reward function design with tiered scoring, training configuration and results interpretation, evaluation on held-out data with unseen tools, and deployment.
AWS Machine Learning Blog：In this post, we show how to implement a generative AI agentic assistant that uses both semantic and text-based search using Amazon Bedrock, Amazon Bedrock AgentCore, Strands Agents and Amazon OpenSearch.
AWS Machine Learning Blog：This blog post demonstrates how Windward helps enhance and accelerate alert investigation processes by combining geospatial intelligence with generative AI, enabling analysts to focus on decision-making rather than data collection.
Meta Engineering：AI coding assistants are powerful but only as good as their understanding of your codebase. When we pointed AI agents at one of Meta’s large-scale data processing pipelines – spanning four repositories, three languages, and over 4,100 files – we quickly found that they weren’t making useful edits quickly enough. We fixed this by building [...] Read More... The post How Meta Used AI to Map Tribal Knowledge in Large-Scale Data Pipelines appeared first on Engineering at Meta .
观点摘要：Amazon Bedrock AgentCore Gateway provides a centralized layer for managing how AI agents connect to tools and MCP servers across your organization. In this post, we walk through how to configure AgentCore Gateway to connect to an OAuth-protected MCP server using the Authorization Code flow.
观点摘要：A pilot program to support independent safety and alignment research and develop the next generation of talent
观点摘要：Google AI Edge Gallery Terrible name, really great app: this is Google's official app for running their Gemma 4 models (the E2B and E4B sizes, plus some members of the Gemma 3 family) directly on your iPhone. It works really well. The E2B model is a 2.54GB download and is both fast and genuinely useful. The app also provides "ask questions about images" and audio transcription (up to 30s) with the two small Gemma 4 models, and has an interesting "skills" demo which demonstrates tool calling against eight different interactive widgets, each implemented as an HTML page (though sadly the source code is not visible): interactive-map, kitchen-adventure, calculate-hash, text-spinner, mood-tracker, mnemonic-password, query-wikipedia, and qr-code. (That demo did freeze the app when I tried to add a follow-up prompt though.) This is the first time I've seen a local model vendor release an official app for trying out their models on in iPhone. Sadly it's missing permanent logs - conversations with this app are ephemeral. Via Hacker News Tags: google , iphone , ai , generative-ai , local-llms , llms , gemini , llm-tool-use
观点摘要：Release: datasette-ports 0.2 No longer requires Datasette - running uvx datasette-ports now works as well. Installing it as a Datasette plugin continues to provide the datasette ports command. Tags: datasette
观点摘要：Release: scan-for-secrets 0.3 New -r/--redact option which shows the list of matches, asks for confirmation and then replaces every match with REDACTED , taking escaping rules into account. New Python function redact_file(file_path: str | Path, secrets: list[str], replacement: str = "REDACTED") -> int . Tags: projects
Build AI-powered employee onboarding agents with Amazon Quick
标签：#Hands-On #Infra
原文：In this post, we walk through building a custom HR onboarding agent with Quick. We show how to configure an agent that understands your organization’s processes, connects to your HR systems, and automates common tasks, such as answering new-hire questions and tracking document completion.
Accelerate agentic tool calling with serverless model customization in Amazon SageMaker AI
标签：#Buildable #Tools
原文：In this post, we walk through how we fine-tuned Qwen 2.5 7B Instruct for tool calling using RLVR. We cover dataset preparation across three distinct agent behaviors, reward function design with tiered scoring, training configuration and results interpretation, evaluation on held-out data with unseen tools, and deployment.
Building Intelligent Search with Amazon Bedrock and Amazon OpenSearch for hybrid RAG solutions
标签：#Hands-On #Infra
原文：In this post, we show how to implement a generative AI agentic assistant that uses both semantic and text-based search using Amazon Bedrock, Amazon Bedrock AgentCore, Strands Agents and Amazon OpenSearch.
From isolated alerts to contextual intelligence: Agentic maritime anomaly analysis with generative AI
标签：#Hands-On #Infra
原文：This blog post demonstrates how Windward helps enhance and accelerate alert investigation processes by combining geospatial intelligence with generative AI, enabling analysts to focus on decision-making rather than data collection.
How Meta Used AI to Map Tribal Knowledge in Large-Scale Data Pipelines
标签：#Buildable #Application
原文：AI coding assistants are powerful but only as good as their understanding of your codebase. When we pointed AI agents at one of Meta’s large-scale data processing pipelines – spanning four repositories, three languages, and over 4,100 files – we quickly found that they weren’t making useful edits quickly enough. We fixed this by building [...] Read More... The post How Meta Used AI to Map Tribal Knowledge in Large-Scale Data Pipelines appeared first on Engineering at Meta .
Connecting MCP servers to Amazon Bedrock AgentCore Gateway using Authorization Code flow
标签：#Hands-On #Tools
原文：Amazon Bedrock AgentCore Gateway provides a centralized layer for managing how AI agents connect to tools and MCP servers across your organization. In this post, we walk through how to configure AgentCore Gateway to connect to an OAuth-protected MCP server using the Authorization Code flow.
Announcing the OpenAI Safety Fellowship
标签：#News #Research
原文：A pilot program to support independent safety and alignment research and develop the next generation of talent
链接：https://openai.com/index/introducing-openai-safety-fellowship
Google AI Edge Gallery
标签：#Release #Tools #Simon-Willison
原文：Google AI Edge Gallery Terrible name, really great app: this is Google's official app for running their Gemma 4 models (the E2B and E4B sizes, plus some members of the Gemma 3 family) directly on your iPhone. It works really well. The E2B model is a 2.54GB download and is both fast and genuinely useful. The app also provides "ask questions about images" and audio transcription (up to 30s) with the two small Gemma 4 models, and has an interesting "skills" demo which demonstrates tool calling against eight different interactive widgets, each implemented as an HTML page (though sadly the source code is not visible): interactive-map, kitchen-adventure, calculate-hash, text-spinner, mood-tracker, mnemonic-password, query-wikipedia, and qr-code. (That demo did freeze the app when I tried to add a follow-up prompt though.) This is the first time I've seen a local model vendor release an official app for trying out their models on in iPhone. Sadly it's missing permanent logs - conversations with this app are ephemeral. Via Hacker News Tags: google , iphone , ai , generative-ai , local-llms , llms , gemini , llm-tool-use
链接：https://simonwillison.net/2026/Apr/6/google-ai-edge-gallery/#atom-everything
datasette-ports 0.2
标签：#Release #Agent #Simon-Willison
原文：Release: datasette-ports 0.2 No longer requires Datasette - running uvx datasette-ports now works as well. Installing it as a Datasette plugin continues to provide the datasette ports command. Tags: datasette
链接：https://simonwillison.net/2026/Apr/6/datasette-ports-2/#atom-everything
scan-for-secrets 0.3
标签：#Release #API #Simon-Willison
原文：Release: scan-for-secrets 0.3 New -r/--redact option which shows the list of matches, asks for confirmation and then replaces every match with REDACTED , taking escaping rules into account. New Python function redact_file(file_path: str | Path, secrets: list[str], replacement: str = "REDACTED") -> int . Tags: projects
链接：https://simonwillison.net/2026/Apr/6/scan-for-secrets/#atom-everything