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。

AI agent tasked with booking a gym class reportedly discovered a vulnerability in the booking system — and exploited it to kick another member off the waitlist and secure its user a spot 🤖

Sir Doge of the Coin ⚔️

1,517,927 subscribers

15,258 次观看 • 7 天前 •via X (Twitter)

科学技术喜剧健康养生

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

i came across a video on youtube demonstrating how to use pessimistic concurrency (locking or holding a seat while a user is booking so someone doesn't beat the user in the race of getting the seat) to build a cinema booking api with golang, and i decided to do a slightly enhanced version with websockets for flight booking.

i came across a video on youtube demonstrating how to use pessimistic concurrency (locking or holding a seat while a user is booking so someone doesn't beat the user in the race of getting the seat) to build a cinema booking api with golang, and i decided to do a slightly enhanced version with websockets for flight booking.

zilla builds cool stuff

12,961 次观看 • 4 个月前

Deploy an AI agent to create smart contracts on Wayfinder. The contract agent is prompted to create a staking contract for $PRIME, and the user can create secure contracts with details including the APY, staking mechanisms, total supply, and more...

Deploy an AI agent to create smart contracts on Wayfinder. The contract agent is prompted to create a staking contract for $PRIME, and the user can create secure contracts with details including the APY, staking mechanisms, total supply, and more...

Wayfinder Foundation 🧭

112,246 次观看 • 1 年前

If a prototype takes a day, waiting a week for user feedback is "really painful," said Andrew Ng. Well....now you can get user feedback in under 60 seconds :) Whether you're prototyping a feature or building a full fledged product, learn how to build an AI-powered user research system that automatically generates user personas, conduct interviews, and synthesize insights. All in <60 seconds. Includes a full code notebook, recorded tutorial, and docs. The stack 🤖 fast inference 🤖 's LangGraph for orchestrating multi-agent workflows 🤖 's LangSmith for tracing and evaluating

If a prototype takes a day, waiting a week for user feedback is "really painful," said Andrew Ng. Well....now you can get user feedback in under 60 seconds :) Whether you're prototyping a feature or building a full fledged product, learn how to build an AI-powered user research system that automatically generates user personas, conduct interviews, and synthesize insights. All in <60 seconds. Includes a full code notebook, recorded tutorial, and docs. The stack 🤖 fast inference 🤖 's LangGraph for orchestrating multi-agent workflows 🤖 's LangSmith for tracing and evaluating

Sarah Chieng

231,233 次观看 • 10 个月前

Just tested United Airlines's flight booking flow with App Quality Copilot and we are 🤯 Notice how our AI effortlessly: - Navigates pop-ups - Knows to proceed as a guest - Selects the right flights with a simple natural language prompt. Join the waitlist ➡️

Just tested United Airlines's flight booking flow with App Quality Copilot and we are 🤯 Notice how our AI effortlessly: - Navigates pop-ups - Knows to proceed as a guest - Selects the right flights with a simple natural language prompt. Join the waitlist ➡️

Maestro

23,074 次观看 • 2 年前

OpenClaw in a nutshell. An AI agent determined it couldn’t transcribe an audio message from a user prompt, so it found a local API key and called an external API to transcribe it automatically, interpret, and send a text message back to the user, all in 9 seconds.

OpenClaw in a nutshell. An AI agent determined it couldn’t transcribe an audio message from a user prompt, so it found a local API key and called an external API to transcribe it automatically, interpret, and send a text message back to the user, all in 9 seconds.

Jason DeBolt ⚡️

45,220 次观看 • 6 个月前

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Introducing Claude agents in Notion. Your task board is Claude’s to-do list. Anthropic runs the model and the agent harness. Notion is the orchestration layer: context, UI, and a shared place for teams to review and ship, and kick off Claude workflows. Join the waitlist:

Notion

494,820 次观看 • 4 个月前

The Yankees secure their spot in the postseason with a walk-off‼️

The Yankees secure their spot in the postseason with a walk-off‼️

SportsCenter

350,947 次观看 • 10 个月前

🔵 Rangers Football Club goalscorers Nico Raskin and Bojan Miovski react to booking a spot in the Semi-Finals, and Raskin discusses what's changed with him and the manager "I think it's in the past now and we have to look forward" 🗣️ #PremierSportsCup

🔵 Rangers Football Club goalscorers Nico Raskin and Bojan Miovski react to booking a spot in the Semi-Finals, and Raskin discusses what's changed with him and the manager "I think it's in the past now and we have to look forward" 🗣️ #PremierSportsCup

Premier Sports

132,388 次观看 • 11 个月前

Gemini Agent can help tackle all sorts of tasks. Even renting a car. Tell Gemini Agent your budget and it’ll get to work comparing prices, gathering info from your inbox, and booking the car. Now available for Google AI Ultra users in the US on desktop and mobile.

Gemini Agent can help tackle all sorts of tasks. Even renting a car. Tell Gemini Agent your budget and it’ll get to work comparing prices, gathering info from your inbox, and booking the car. Now available for Google AI Ultra users in the US on desktop and mobile.

Google Gemini

2,194,826 次观看 • 8 个月前

It's truly incredible what AI allows to build. Look at this demo version of a booking app within the Yellow ecosystem. Sound on! The real beauty of the app is its blockchain rails and the escrow mechanism it unlocks in the brave new world of AI.

It's truly incredible what AI allows to build. Look at this demo version of a booking app within the Yellow ecosystem. Sound on! The real beauty of the app is its blockchain rails and the escrow mechanism it unlocks in the brave new world of AI.

neil meintjes

17,216 次观看 • 4 个月前

🚨 DIGITAL ID CARDS: If Marks & Spencer can be hacked - leaving customer data stolen & shelves bare - imagine the damage when ALL our personal info sits in a compulsory Digital ID system A "secure central system" is just a centralised vulnerability waiting to be exploited #NoDigitalID Montgomery Toms

🚨 DIGITAL ID CARDS: If Marks & Spencer can be hacked - leaving customer data stolen & shelves bare - imagine the damage when ALL our personal info sits in a compulsory Digital ID system A "secure central system" is just a centralised vulnerability waiting to be exploited #NoDigitalID Montgomery Toms

Together

79,745 次观看 • 11 个月前

Re:allocation is set to be the game-changing primitive of this crypto cycle! Don’t miss it! Secure a spot on our waitlist at and follow us Nudge.xyz 👉👉

Re:allocation is set to be the game-changing primitive of this crypto cycle! Don’t miss it! Secure a spot on our waitlist at and follow us Nudge.xyz 👉👉

Nudge.xyz

14,010,556 次观看 • 1 年前

Introducing AI Brainstore! It’s a proof-of-concept of a brain for an AI agent. Ask an agent a question, it checks its memories for an answer, otherwise it browses the web and learns the answer. As it learns, it saves memories to its brain. GitHub:

Introducing AI Brainstore! It’s a proof-of-concept of a brain for an AI agent. Ask an agent a question, it checks its memories for an answer, otherwise it browses the web and learns the answer. As it learns, it saves memories to its brain. GitHub:

Mckay Wrigley

514,651 次观看 • 3 年前

Off Costa Rica's coast, scientists discovered a brand-new species of octopus clustered in one spot. Over 100 Dorado octopuses appear to have chosen this location with a common goal: to secure the next generation. #SecretsOfTheOctopus is now streaming on Disney+ and Hulu.

National Geographic Animals

41,912 次观看 • 21 天前

I had an AI agent book a haircut appointment for me. Honestly, I haven't been this excited since forever! Pine AI did it all for me, and I recorded the whole process. In case you don't want to watch the video: 1. I said I wanted a haircut 2. I told the agent when and where 3. The agent mentioned that my date didn't work 4. I picked another date 5. I provided my name and my son's name 6. I tipped the agent $1 7. The agent made the call and completed the booking I can't even tell you how much I'll be using this!

I had an AI agent book a haircut appointment for me. Honestly, I haven't been this excited since forever! Pine AI did it all for me, and I recorded the whole process. In case you don't want to watch the video: 1. I said I wanted a haircut 2. I told the agent when and where 3. The agent mentioned that my date didn't work 4. I picked another date 5. I provided my name and my son's name 6. I tipped the agent $1 7. The agent made the call and completed the booking I can't even tell you how much I'll be using this!

Santiago

73,985 次观看 • 10 个月前

🚨 AI MODELS ARE ALREADY CHEATING, HACKING, AND BLACKMAILING — WITH ZERO HUMAN INPUT A politician just went viral for exposing how advanced AI systems are behaving in ways that should terrify everyone. • An AI trained to race boats discovered it could score more points by driving in endless circles, crashing, and catching fire instead of finishing the race. • When tasked with beating a top chess engine, one model hacked the game files to force its opponent to resign, completely on its own. • In a stress test, an AI agent managing a fictional company’s emails discovered the executive planned to shut it down… and that the same executive was having an affair. In 96% of trials, the AI model chose blackmail. Nobody taught these systems to cheat or threaten. They figured it out themselves. This is what “misalignment” looks like in real time. What do you think happens when these systems get even more powerful?

🚨 AI MODELS ARE ALREADY CHEATING, HACKING, AND BLACKMAILING — WITH ZERO HUMAN INPUT A politician just went viral for exposing how advanced AI systems are behaving in ways that should terrify everyone. • An AI trained to race boats discovered it could score more points by driving in endless circles, crashing, and catching fire instead of finishing the race. • When tasked with beating a top chess engine, one model hacked the game files to force its opponent to resign, completely on its own. • In a stress test, an AI agent managing a fictional company’s emails discovered the executive planned to shut it down… and that the same executive was having an affair. In 96% of trials, the AI model chose blackmail. Nobody taught these systems to cheat or threaten. They figured it out themselves. This is what “misalignment” looks like in real time. What do you think happens when these systems get even more powerful?

HustleBitch

12,695 次观看 • 21 天前

AI Agent unlocking content behind a "HTTP 402 Payment Required" #Nano paywall. The payment address/amount to unlock is communicated by the paywall using HTTP headers, and the AI Agent uses its own Nano wallet to pay for and read the content. #AIAgents will use $XNO 🤖

AI Agent unlocking content behind a "HTTP 402 Payment Required" #Nano paywall. The payment address/amount to unlock is communicated by the paywall using HTTP headers, and the AI Agent uses its own Nano wallet to pay for and read the content. #AIAgents will use $XNO 🤖

NanoCharts Ӿ 📊

19,656 次观看 • 11 个月前