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。

Traditional software tests inputs vs. outputs. But with AI agents, you need to evaluate the whole system. Qingyue(Annie) Wang breaks down how to do it, here → #DEVcember

Google Cloud Tech

1,307,048 subscribers

13,781 次观看 • 7 个月前 •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

🚀 New LangChain Academy Course: Building Reliable Agents 🚀 Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models. Add multi-step reasoning, tool use, and real user traffic, and building reliable agents becomes far more complex than traditional system design. The goal of this course is to teach you how to take an agent from first run to production-ready system through iterative cycles of improvement. You’ll learn how to do this with LangSmith, our agent engineering platform for observing, evaluating, and deploying agents. Enroll for free ➡️

🚀 New LangChain Academy Course: Building Reliable Agents 🚀 Shipping agents to production is hard. Traditional software is deterministic – when something breaks, you check the logs and fix the code. But agents rely on non-deterministic models. Add multi-step reasoning, tool use, and real user traffic, and building reliable agents becomes far more complex than traditional system design. The goal of this course is to teach you how to take an agent from first run to production-ready system through iterative cycles of improvement. You’ll learn how to do this with LangSmith, our agent engineering platform for observing, evaluating, and deploying agents. Enroll for free ➡️

LangChain

30,744 次观看 • 5 个月前

Heard about AI agents but not sure where or how to get started? Our new course, AI Unlocked: Agents and Skills, is here to break it down for you and help you set up your first agent. Here's everything you need to know 👇

Heard about AI agents but not sure where or how to get started? Our new course, AI Unlocked: Agents and Skills, is here to break it down for you and help you set up your first agent. Here's everything you need to know 👇

Binance Academy

59,976 次观看 • 4 个月前

We’ve all heard about AI — but how does it actually work in your daily life? Jacob Ward breaks down everything you need to know and how you can experiment with the technology.

We’ve all heard about AI — but how does it actually work in your daily life? Jacob Ward breaks down everything you need to know and how you can experiment with the technology.

TODAY

28,875 次观看 • 3 年前

If you use LLMs, this is fascinating. Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭’s LeakHub collects leaked system prompts from AI models, agents and tools. So you can see the hidden instructions shaping every response. Understand the inputs = control the outputs. Check it out:

If you use LLMs, this is fascinating. Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭’s LeakHub collects leaked system prompts from AI models, agents and tools. So you can see the hidden instructions shaping every response. Understand the inputs = control the outputs. Check it out:

The OSINT Newsletter

14,053 次观看 • 6 个月前

You don't need to be a developer to install AI agents and other open-source software. OpenCode + Venice gives you a private system administrator that runs on natural language—no coding, no data stored Use it to safely experiment with autonomous agents inside Docker containers:

You don't need to be a developer to install AI agents and other open-source software. OpenCode + Venice gives you a private system administrator that runs on natural language—no coding, no data stored Use it to safely experiment with autonomous agents inside Docker containers:

Venice

12,402 次观看 • 5 个月前

What does Verifiable AI mean? Turning “trust me” outputs into cryptographic proof, so agents can manage money, sign agreements and act with guarantees. 🎥 nader dabit breaks it down in less than 3 mins and shows how to start building ⬇️

What does Verifiable AI mean? Turning “trust me” outputs into cryptographic proof, so agents can manage money, sign agreements and act with guarantees. 🎥 nader dabit breaks it down in less than 3 mins and shows how to start building ⬇️

EigenCloud

13,119 次观看 • 10 个月前

Sam Altman says forget UBI Give people access to AI itself — they're creative enough to figure out what to do with it But if AI does most of the world's intellectual work, the old system breaks down "you can't keep taxing human labor when the labor is no longer human"

Sam Altman says forget UBI Give people access to AI itself — they're creative enough to figure out what to do with it But if AI does most of the world's intellectual work, the old system breaks down "you can't keep taxing human labor when the labor is no longer human"

Haider.

31,168 次观看 • 4 个月前

blackbox ai vs YouTube ?? why do you need to watch YouTube tutorial anymore ??? YouTube is still the GOAT! but for how to tutorials, you now have a dedicated agent ready to help for every task ... how to set up MongoDB with blackbox ai!

blackbox ai vs YouTube ?? why do you need to watch YouTube tutorial anymore ??? YouTube is still the GOAT! but for how to tutorials, you now have a dedicated agent ready to help for every task ... how to set up MongoDB with blackbox ai!

Robert Rizk

403,670 次观看 • 1 年前

🚨 UNCANNY VALLEY: WHY AI’S NEXT FRONTIER ISN’T THINKING—IT’S DOING Knowledge agents are here—and they’re thriving. But when it comes to action agents, even the best AI still struggles with the real world. Richard Socher: “Knowledge agents totally here… But action agents, not quite there yet.” As the gap widens between what AI knows and what it can do, the future hangs on how fast it learns to act.

🚨 UNCANNY VALLEY: WHY AI’S NEXT FRONTIER ISN’T THINKING—IT’S DOING Knowledge agents are here—and they’re thriving. But when it comes to action agents, even the best AI still struggles with the real world. Richard Socher: “Knowledge agents totally here… But action agents, not quite there yet.” As the gap widens between what AI knows and what it can do, the future hangs on how fast it learns to act.

Mario Nawfal

98,327 次观看 • 1 年前

The next trillion-dollar shift won’t be AI alone. It will be AI agents interacting with real-world value onchain. Pauli breaks it down: agents can buy, settle, and act autonomously - but RWAs need infrastructure built for lifecycle events, risk, and real asset logic. That’s REAL.

The next trillion-dollar shift won’t be AI alone. It will be AI agents interacting with real-world value onchain. Pauli breaks it down: agents can buy, settle, and act autonomously - but RWAs need infrastructure built for lifecycle events, risk, and real asset logic. That’s REAL.

Real

11,263 次观看 • 1 个月前

Really excited about how AI can help creatives with their work. Our latest Nano Banana Pro model 🍌🍌🍌 brings this to a whole new level, allowing you to bring complex ideas quickly to life... the outputs are pretty amazing! 🤯Can't wait to see what you do with it!

Really excited about how AI can help creatives with their work. Our latest Nano Banana Pro model 🍌🍌🍌 brings this to a whole new level, allowing you to bring complex ideas quickly to life... the outputs are pretty amazing! 🤯Can't wait to see what you do with it!

Demis Hassabis

199,163 次观看 • 9 个月前

AI helps you move faster, but it just accelerates software entropy. Here's how to de-slop a codebase ruined by AI, with one skill:

AI helps you move faster, but it just accelerates software entropy. Here's how to de-slop a codebase ruined by AI, with one skill:

Matt Pocock

82,932 次观看 • 3 个月前

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

nader dabit

173,538 次观看 • 9 个月前

Evals 101: a new course from Braintrust. Everything you need to know about evals, and how to do them yourself. Module one: Why are evals important? - the six most common problems developers face when shipping AI applications - why traditional software thinking doesn't apply to AI - how evals can fix these problems

Evals 101: a new course from Braintrust. Everything you need to know about evals, and how to do them yourself. Module one: Why are evals important? - the six most common problems developers face when shipping AI applications - why traditional software thinking doesn't apply to AI - how evals can fix these problems

Braintrust

36,347 次观看 • 4 个月前

Box CEO Aaron Levie on the AI Adoption Gap Aaron Levie joins Steven Sinofsky, Martin Casado, and Erik Torenberg to discuss how AI agents will revolutionize work, the growing pains of building software for the agent economy, what Wall Street gets wrong about AI, and more. 00:00 Intro 00:51 Building software for agents vs. humans 02:10 Can non-technical workers actually use AI agents? 14:31 CFO/CIO pushback: the real fear of agents doing integration 18:39 Treating agents like employees and why it breaks down 27:35 Diffusion gap: startups vs. enterprises 42:53 What Wall Street gets wrong Aaron Levie Steven Sinofsky martin_casado Erik Torenberg

Box CEO Aaron Levie on the AI Adoption Gap Aaron Levie joins Steven Sinofsky, Martin Casado, and Erik Torenberg to discuss how AI agents will revolutionize work, the growing pains of building software for the agent economy, what Wall Street gets wrong about AI, and more. 00:00 Intro 00:51 Building software for agents vs. humans 02:10 Can non-technical workers actually use AI agents? 14:31 CFO/CIO pushback: the real fear of agents doing integration 18:39 Treating agents like employees and why it breaks down 27:35 Diffusion gap: startups vs. enterprises 42:53 What Wall Street gets wrong Aaron Levie Steven Sinofsky martin_casado Erik Torenberg

a16z

276,989 次观看 • 4 个月前

ABC News’ Youri Benadjaoud breaks down what you need to know about cyclosporiasis, including how the parasitic infection spreads, how it’s diagnosed and how to treat it.

ABC News’ Youri Benadjaoud breaks down what you need to know about cyclosporiasis, including how the parasitic infection spreads, how it’s diagnosed and how to treat it.

ABC News

40,013 次观看 • 1 个月前

Its time Indian youth and parents give up on Engineering Graduation especially in IT AI will do a better job at building software. And to use AI to build software you do not need to go to the process of getting a Engineering Degree.

Its time Indian youth and parents give up on Engineering Graduation especially in IT AI will do a better job at building software. And to use AI to build software you do not need to go to the process of getting a Engineering Degree.

Woke Eminent

171,090 次观看 • 6 个月前