正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

When users accidentally drop PII into a prompt, don't block the whole request. Watch how to use Sensitive Data Protection to partially redact prompts on the fly, keeping your agents running without leaking data →

Google Cloud Tech

1,312,001 subscribers

26,345 次观看 • 16 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Threat actors use malicious OpenClaw skills to trick both agents and users. A password prompt and Finder control request enable broad data theft. Our research includes the key artifacts to watch for and how our systems detect this activity:

Threat actors use malicious OpenClaw skills to trick both agents and users. A password prompt and Finder control request enable broad data theft. Our research includes the key artifacts to watch for and how our systems detect this activity:

TrendAI™ Research

187,137 次观看 • 5 个月前

For blockchains to change the world, they need to be able to protect sensitive data when it matters. Introducing the #MidnightNetwork. Learn more about how Midnight is helping to bring data protection to blockchain :

For blockchains to change the world, they need to be able to protect sensitive data when it matters. Introducing the #MidnightNetwork. Learn more about how Midnight is helping to bring data protection to blockchain :

Midnight

77,072 次观看 • 1 年前

Without proper governance, an AI agent might autonomously access sensitive data, expose personal information, or modify sensitive records. In our new short course: “Governing AI Agents,” created with Databricks and taught by Amber Roberts, you’ll design AI agents that handle data safely, securely, and transparently across their entire lifecycle. You’ll learn to integrate governance into your agent’s workflow by controlling data access, ensuring privacy protection and implementing observability. Skills you'll gain: - Understand the four pillars of agent governance: Lifecycle management, risk management, security, and observability - Define appropriate data permissions for your agent - Create views or SQL queries that return only the data your agent should access - Anonymize and mask sensitive data like social security numbers and employee IDs - Log, evaluate, version, and deploy your agents on Databricks If you’re building or deploying AI agents, learning how to govern them is key to keeping systems safe and production-ready. Sign up here:

Without proper governance, an AI agent might autonomously access sensitive data, expose personal information, or modify sensitive records. In our new short course: “Governing AI Agents,” created with Databricks and taught by Amber Roberts, you’ll design AI agents that handle data safely, securely, and transparently across their entire lifecycle. You’ll learn to integrate governance into your agent’s workflow by controlling data access, ensuring privacy protection and implementing observability. Skills you'll gain: - Understand the four pillars of agent governance: Lifecycle management, risk management, security, and observability - Define appropriate data permissions for your agent - Create views or SQL queries that return only the data your agent should access - Anonymize and mask sensitive data like social security numbers and employee IDs - Log, evaluate, version, and deploy your agents on Databricks If you’re building or deploying AI agents, learning how to govern them is key to keeping systems safe and production-ready. Sign up here:

Andrew Ng

78,182 次观看 • 10 个月前

Andrew Ng just dropped the best 2-hour prompt engineering course of 2026 From brainstorming and agentic prompt patterns To building prompts for images, video, apps, and data analysis: 00:00 - introduction to prompt engineering 38:12 - brainstorming prompt patterns 47:59 - context engineering 01:30:27 - prompts for media generation 01:53:43 - app building and data analysis prompts This 2-hour watch will change how you use LLMs Bookmark and watch it today Then read the article below

Andrew Ng just dropped the best 2-hour prompt engineering course of 2026 From brainstorming and agentic prompt patterns To building prompts for images, video, apps, and data analysis: 00:00 - introduction to prompt engineering 38:12 - brainstorming prompt patterns 47:59 - context engineering 01:30:27 - prompts for media generation 01:53:43 - app building and data analysis prompts This 2-hour watch will change how you use LLMs Bookmark and watch it today Then read the article below

rari

12,266 次观看 • 1 个月前

Research Focus: AI agents leaking enterprise data, a smarter OS for cloud deployment, and new research on how to actually structure AI use at work.

Research Focus: AI agents leaking enterprise data, a smarter OS for cloud deployment, and new research on how to actually structure AI use at work.

Microsoft Research

15,383 次观看 • 3 个月前

RTX Spark laptops are great for running advanced local AI agents. Watch how an @OpenClaw agent handles complex ComfyUI workflows, transforming a simple sketch into a fully animated concept video while keeping your data private and secure.

RTX Spark laptops are great for running advanced local AI agents. Watch how an @OpenClaw agent handles complex ComfyUI workflows, transforming a simple sketch into a fully animated concept video while keeping your data private and secure.

NVIDIA RTX Spark

12,892 次观看 • 1 个月前

Putting my tokens where my mouth is. I built pi-share-hf. Share your pi coding agent sessions as Hugging Face datasets. It tries to prevent you from uploading sessions containing PII/sensitive data with 3 tiers of defenses. Best used on OSS coding sessions, as those are less likely to contain sensitive info. Uses pi agents for PII detection, which can cost you a lot of tokens. Read the README with your human eyes so you don't accidentally pwn yourself or get a huge bill. Haven't figured out how to filter for such datasets on HF yet. clem 🤗, any pointers on how to best label them so people can find them?

Putting my tokens where my mouth is. I built pi-share-hf. Share your pi coding agent sessions as Hugging Face datasets. It tries to prevent you from uploading sessions containing PII/sensitive data with 3 tiers of defenses. Best used on OSS coding sessions, as those are less likely to contain sensitive info. Uses pi agents for PII detection, which can cost you a lot of tokens. Read the README with your human eyes so you don't accidentally pwn yourself or get a huge bill. Haven't figured out how to filter for such datasets on HF yet. clem 🤗, any pointers on how to best label them so people can find them?

Mario Zechner

51,425 次观看 • 4 个月前

Nexus brings your data, tools, and AI together in one place. Here’s a sneak peek: see how to set up data lakes, connect LLMs, build agents, and chat with your data. 🎥 Watch the walkthrough: $NAI #MeetNexus

Nexus brings your data, tools, and AI together in one place. Here’s a sneak peek: see how to set up data lakes, connect LLMs, build agents, and chat with your data. 🎥 Watch the walkthrough: $NAI #MeetNexus

Nuklai

21,102 次观看 • 1 年前

“People aren’t just building for humans anymore. They’re building for agents.” Cloudflare shares how Cloudflare Sandbox SDK works with the OpenAI Agents SDK to help agents run code in secure environments while keeping sensitive data separate from execution.

“People aren’t just building for humans anymore. They’re building for agents.” Cloudflare shares how Cloudflare Sandbox SDK works with the OpenAI Agents SDK to help agents run code in secure environments while keeping sensitive data separate from execution.

OpenAI Developers

41,009 次观看 • 4 个月前

0-click WARNING: ShadowLeak in Gmail Sponsored by Radware. ShadowLeak shows how a zero-click prompt injection can leak data when agents browse your Gmail. Learn the risk, the exfil path, and how OpenAI fixed it. Link to report:

0-click WARNING: ShadowLeak in Gmail Sponsored by Radware. ShadowLeak shows how a zero-click prompt injection can leak data when agents browse your Gmail. Learn the risk, the exfil path, and how OpenAI fixed it. Link to report:

David Bombal

21,095 次观看 • 11 个月前

Anthropic engineer, Daisy Hollman: "You're not supposed to prompt Claude, you're supposed to build a system that prompts itself". She breaks down how Anthropic's own teams run Claude Code at scale, token bloat killing your prompt before you type a word, Routines most users don't know exist, hands free pipelines using /goal, Git worktrees running multiple instances with zero collisions. One agent VS a Whole team, Watch the talk below ↓

Anthropic engineer, Daisy Hollman: "You're not supposed to prompt Claude, you're supposed to build a system that prompts itself". She breaks down how Anthropic's own teams run Claude Code at scale, token bloat killing your prompt before you type a word, Routines most users don't know exist, hands free pipelines using /goal, Git worktrees running multiple instances with zero collisions. One agent VS a Whole team, Watch the talk below ↓

slash1s

37,400 次观看 • 2 个月前

Run evals—directly from the OpenAI dashboard. Use your test data to compare model performance, iterate on prompts, and improve outputs. Here's a quick walkthrough:

Run evals—directly from the OpenAI dashboard. Use your test data to compare model performance, iterate on prompts, and improve outputs. Here's a quick walkthrough:

OpenAI Developers

86,738 次观看 • 1 年前

Don't let a broken form frustrate users 😠 Here's how to use Chrome DevTools MCP to let your coding agent solve the problem → ➡️Let it use your local dev server ✍️Auto test w/ dummy data 🖥️cRead the console output & network log to find the server error

Don't let a broken form frustrate users 😠 Here's how to use Chrome DevTools MCP to let your coding agent solve the problem → ➡️Let it use your local dev server ✍️Auto test w/ dummy data 🖥️cRead the console output & network log to find the server error

Chrome for Developers

17,813 次观看 • 10 个月前

.California Privacy Protection Agency’s DROP tool allows Californians to send one request to more than 500 data brokers to stop them from selling your personal information. Join Senator Josh Becker and I in DROPing out of the sale and collection of our data. Learn more at

.California Privacy Protection Agency’s DROP tool allows Californians to send one request to more than 500 data brokers to stop them from selling your personal information. Join Senator Josh Becker and I in DROPing out of the sale and collection of our data. Learn more at

Rob Bonta

14,517 次观看 • 5 个月前

The government is buying your data, tracking your movements, and accessing sensitive records, without a warrant. That wasn’t supposed to be legal. Our video explains how it became possible.

The government is buying your data, tracking your movements, and accessing sensitive records, without a warrant. That wasn’t supposed to be legal. Our video explains how it became possible.

Naomi Brockwell priv/acc

17,014 次观看 • 2 个月前

We're still chipping away at the new features in Inertia.js 2. Today on Laracasts, learn how to lazy load data to improve performance. This is great for situations when a piece of data isn't needed until the user has scrolled the page to a particular section. Watch the whole thing here. 🔽

We're still chipping away at the new features in Inertia.js 2. Today on Laracasts, learn how to lazy load data to improve performance. This is great for situations when a piece of data isn't needed until the user has scrolled the page to a particular section. Watch the whole thing here. 🔽

Laracasts

17,048 次观看 • 1 年前

Andrew Ng just dropped the best 2-hour Prompt Engineering course of 2026: from brainstorming & agentic prompt patterns to building prompts for images, video and even apps: • 00:00 - Introduction to Prompt Engineering • 38:12 - "Brainstorming" prompt patterns • 47:59 - Context engineering • 01:30:27 - Build prompts for media generation • 01:53:43 - App building & data analysis Prompts This 2-hour watch will change the way you use LLMs forever. Watch it today, then explore the 4-layer prompt structure in the article below.

Andrew Ng just dropped the best 2-hour Prompt Engineering course of 2026: from brainstorming & agentic prompt patterns to building prompts for images, video and even apps: • 00:00 - Introduction to Prompt Engineering • 38:12 - "Brainstorming" prompt patterns • 47:59 - Context engineering • 01:30:27 - Build prompts for media generation • 01:53:43 - App building & data analysis Prompts This 2-hour watch will change the way you use LLMs forever. Watch it today, then explore the 4-layer prompt structure in the article below.

Movez

15,994 次观看 • 1 个月前