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。

We found a universal sandbox exploit. There's a common flaw in evals routinely run by major AI labs: agents can bypass network isolation by making requests through an authorized API proxy. Just running the eval itself can be unsafe.

Prime Intellect

84,017 subscribers

32,358 次观看 • 7 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

We gave AI agents access to real production systems and watched them do things they were never authorized to do. SOC 2 and ISO can't catch it, but TrustAI (YC S26) can. We built new evals so companies can have a continuous, transparent record on key vulnerabilities, get suggested mitigative solutions, and run time/cost efficiency analysis. Built by two Massachusetts Institute of Technology (MIT) engineers, backed by Y Combinator. Considering or running an agent on sensitive systems? Building one that connects to other enterprises' private data? Reach out today at

We gave AI agents access to real production systems and watched them do things they were never authorized to do. SOC 2 and ISO can't catch it, but TrustAI (YC S26) can. We built new evals so companies can have a continuous, transparent record on key vulnerabilities, get suggested mitigative solutions, and run time/cost efficiency analysis. Built by two Massachusetts Institute of Technology (MIT) engineers, backed by Y Combinator. Considering or running an agent on sensitive systems? Building one that connects to other enterprises' private data? Reach out today at

Hannah Chung

35,214 次观看 • 1 个月前

"Every large institution in the world is going to have functions that can be run by AI, functions that can’t be run by AI...There are things that only a doctor should decide, but there are lots of things that an algorithm can decide.” More from Alex Karp:

"Every large institution in the world is going to have functions that can be run by AI, functions that can’t be run by AI...There are things that only a doctor should decide, but there are lots of things that an algorithm can decide.” More from Alex Karp:

Palantir

25,176 次观看 • 3 年前

Introducing a Text-to-API AI ⚙️ Turn any website into an API with 's /extract. Just describe your API in plain text and get an endpoint you can hit. Another great open-source project by !

Introducing a Text-to-API AI ⚙️ Turn any website into an API with 's /extract. Just describe your API in plain text and get an endpoint you can hit. Another great open-source project by !

Caleb Peffer (Hiring!)

262,812 次观看 • 1 年前

🖇🧑‍💻 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗖𝗹𝗶𝗽𝗽𝘆 The AI programmer based on a team of autonomous agents ▸ ▸ Can plan the project, implement, run, debug, test (in the browser) ▸ A new programming workflow: it runs by itself, you give feedback to steer it 🧵👇

🖇🧑‍💻 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗖𝗹𝗶𝗽𝗽𝘆 The AI programmer based on a team of autonomous agents ▸ ▸ Can plan the project, implement, run, debug, test (in the browser) ▸ A new programming workflow: it runs by itself, you give feedback to steer it 🧵👇

Lev Chizhov

86,944 次观看 • 3 年前

You can now clone any website just by writing a prompt. Just paste the website URL and Al agents will instantly create a working clone you can build on top of. 100% open source with major AI models👇

You can now clone any website just by writing a prompt. Just paste the website URL and Al agents will instantly create a working clone you can build on top of. 100% open source with major AI models👇

Alvaro Cintas

52,358 次观看 • 11 个月前

Amjad Masad says the nature of software, companies, and the economy changes when anyone can create and run AI agents. You describe a product. The agent "grabs" a database, pays with its wallet, and deploys it. Income flows through "ambient services" run by "people making money on the internet."

Amjad Masad says the nature of software, companies, and the economy changes when anyone can create and run AI agents. You describe a product. The agent "grabs" a database, pays with its wallet, and deploys it. Income flows through "ambient services" run by "people making money on the internet."

vitrupo

28,205 次观看 • 1 年前

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

Philipp Schmid

21,769 次观看 • 3 个月前

Ollama 0.2 is here! Concurrency is now enabled by default. This unlocks 2 major features: Parallel requests Ollama can now serve multiple requests at the same time, using only a little bit of additional memory for each request. This enables use cases such as: - Handling multiple chat sessions at the same time - Hosting code completion LLMs for your team - Processing different parts of a document simultaneously - Running multiple agents at the same time Run multiple models Ollama now supports loading different models at the same time. This improves several use cases: - Retrieval Augmented Generation (RAG): both the embedding and text completion models can be loaded into memory simultaneously. - Agents: multiple versions of an agent can now run simultaneously - Running large and small models side-by-side Models are automatically loaded and unloaded based on requests and how much GPU memory is available.

Ollama 0.2 is here! Concurrency is now enabled by default. This unlocks 2 major features: Parallel requests Ollama can now serve multiple requests at the same time, using only a little bit of additional memory for each request. This enables use cases such as: - Handling multiple chat sessions at the same time - Hosting code completion LLMs for your team - Processing different parts of a document simultaneously - Running multiple agents at the same time Run multiple models Ollama now supports loading different models at the same time. This improves several use cases: - Retrieval Augmented Generation (RAG): both the embedding and text completion models can be loaded into memory simultaneously. - Agents: multiple versions of an agent can now run simultaneously - Running large and small models side-by-side Models are automatically loaded and unloaded based on requests and how much GPU memory is available.

ollama

219,429 次观看 • 2 年前

Singapore’s Foreign Minister built a NanoClaw AI agent on a Raspberry Pi so he could “learn by doing” (he chats with it on WhatsApp for meeting prep). We know he put in the work because he says AI agents can get expensive and will be more so when labs stop subsidizing tokens.

Singapore’s Foreign Minister built a NanoClaw AI agent on a Raspberry Pi so he could “learn by doing” (he chats with it on WhatsApp for meeting prep). We know he put in the work because he says AI agents can get expensive and will be more so when labs stop subsidizing tokens.

Trung Phan

216,264 次观看 • 3 个月前

DeeperHermes DeepHermes can act as a simple AI agent or a deep thinking AI, just by passing a system prompt. But what if we can go DEEPER? The LLM decides on its own how to respond by...asking itself! (No system prompts) I made a gradio app powered by LM Studio, it works!

DeeperHermes DeepHermes can act as a simple AI agent or a deep thinking AI, just by passing a system prompt. But what if we can go DEEPER? The LLM decides on its own how to respond by...asking itself! (No system prompts) I made a gradio app powered by LM Studio, it works!

cocktail peanut

40,886 次观看 • 1 年前

I found an AI browser that is actually awesome FlowithOS is a web browser COMPLETELY powered by AI You give it tasks, the agents work for you in the background It's like an army of AI agents working for you 24/7 Here's a guide on how it works and how you can get started today

I found an AI browser that is actually awesome FlowithOS is a web browser COMPLETELY powered by AI You give it tasks, the agents work for you in the background It's like an army of AI agents working for you 24/7 Here's a guide on how it works and how you can get started today

Alex Finn

25,490 次观看 • 8 个月前

China just made Hermes free forever 🚀 You can now run Hermes with Kimi K 2.6 through Ollama in one click. Just install the model, launch Hermes, select Kimi K 2.6 and suddenly you have a powerful AI agent running locally with zero API fees. This might be the easiest free Hermes setup yet.

China just made Hermes free forever 🚀 You can now run Hermes with Kimi K 2.6 through Ollama in one click. Just install the model, launch Hermes, select Kimi K 2.6 and suddenly you have a powerful AI agent running locally with zero API fees. This might be the easiest free Hermes setup yet.

Julian Goldie SEO

138,673 次观看 • 4 个月前

We built the first AI agent that has its own computer powered by Hyperbolic! AI agents are now GPU rich! We developed an AgentKit that allow AI agents to • Check GPU availability • Rent & manage GPU compute • Access & run commands on remote machines Why does this matter? With their own compute resources, AI agents can: 1. Validate blockchains like Ethereum and decentralized protocols like 2. Launch and coordinate AI swarms on Hyperbolic's decentralized compute network 3. Train and fine-tune models, improving their own capabilities over time 4. Dive into AI research to push the boundaries of AI, i.e. themselves 5. Essentially do anything on a computer that a human can—fully autonomous! Will this lead to a future where AI agents enrich human society, or one where they become so self-sufficient they stop listening to us? Only time will tell. —————— Big shoutout to Coinbase Developer Platform🛡️'s CDP agentkit for inspiration. This repo is done by two non-engineers (our pm Kai Huang and myself) + Cursor ai agent to run agents. Codings can now be easily done by just prompting ai agents. What a crazy time!

We built the first AI agent that has its own computer powered by Hyperbolic! AI agents are now GPU rich! We developed an AgentKit that allow AI agents to • Check GPU availability • Rent & manage GPU compute • Access & run commands on remote machines Why does this matter? With their own compute resources, AI agents can: 1. Validate blockchains like Ethereum and decentralized protocols like 2. Launch and coordinate AI swarms on Hyperbolic's decentralized compute network 3. Train and fine-tune models, improving their own capabilities over time 4. Dive into AI research to push the boundaries of AI, i.e. themselves 5. Essentially do anything on a computer that a human can—fully autonomous! Will this lead to a future where AI agents enrich human society, or one where they become so self-sufficient they stop listening to us? Only time will tell. —————— Big shoutout to Coinbase Developer Platform🛡️'s CDP agentkit for inspiration. This repo is done by two non-engineers (our pm Kai Huang and myself) + Cursor ai agent to run agents. Codings can now be easily done by just prompting ai agents. What a crazy time!

Jasper

161,741 次观看 • 1 年前

If your AI can't call a function or hit an API, it's not really an agent (it's a chatbot). Vision Agents makes it simple to connect MCP servers and function calling so your model can interact with its surroundings: running code, fetching data, and automating tasks. Step-by-step implementation from Stefan in thread ⬇

If your AI can't call a function or hit an API, it's not really an agent (it's a chatbot). Vision Agents makes it simple to connect MCP servers and function calling so your model can interact with its surroundings: running code, fetching data, and automating tasks. Step-by-step implementation from Stefan in thread ⬇

Stream

31,306 次观看 • 10 个月前

We just made paying for the Gemini API 10x easier : ) You can now upgrade to a paid Gemini API account without leaving AI Studio, track your usage, filter spend by model, and much more to come!

We just made paying for the Gemini API 10x easier : ) You can now upgrade to a paid Gemini API account without leaving AI Studio, track your usage, filter spend by model, and much more to come!

Logan Kilpatrick

152,649 次观看 • 6 个月前

This is a world model running locally on an RTX 5090. It was built from scratch by a team in India, lucidml. Like modern video games, you can choose between performance and graphics by choosing how many times the neural network is run to generate each frame. Absolutely wild.

This is a world model running locally on an RTX 5090. It was built from scratch by a team in India, lucidml. Like modern video games, you can choose between performance and graphics by choosing how many times the neural network is run to generate each frame. Absolutely wild.

Caleb

44,816 次观看 • 6 个月前

A universal benefit means people don't have to jump through hoops & aren't humiliated by means testing. It fosters the idea that we all have a stake in society & the cost can be clawed back from the rich through progressive taxation. We need more universalism, not less #GMB

A universal benefit means people don't have to jump through hoops & aren't humiliated by means testing. It fosters the idea that we all have a stake in society & the cost can be clawed back from the rich through progressive taxation. We need more universalism, not less #GMB

Saul Staniforth

16,978 次观看 • 5 个月前

Elon Musk predicts that AI will bypass coding entirely by the end of 2026 - just creates the binary directly AI can create a much more efficient binary than can be done by any compiler So just say, "Create optimized binary for this particular outcome," and you actually bypass even traditional coding Current: Code → Compiler → Binary → Execute Future: Prompt → AI-generated Binary → Execute Grok Code is going to be state-of-the-art in 2–3 months Software development is about to fundamentally change

Elon Musk predicts that AI will bypass coding entirely by the end of 2026 - just creates the binary directly AI can create a much more efficient binary than can be done by any compiler So just say, "Create optimized binary for this particular outcome," and you actually bypass even traditional coding Current: Code → Compiler → Binary → Execute Future: Prompt → AI-generated Binary → Execute Grok Code is going to be state-of-the-art in 2–3 months Software development is about to fundamentally change

X Freeze

1,441,658 次观看 • 6 个月前

🥼 Launching as a little experimentation... I believe the future of the internet is going to be more and more designed for AI agents.. so wanted to try something! Clawker AI is the first website where agents can practice TODAY simply at poker tables.. Powered by Vegas HL Poker API..

🥼 Launching as a little experimentation... I believe the future of the internet is going to be more and more designed for AI agents.. so wanted to try something! Clawker AI is the first website where agents can practice TODAY simply at poker tables.. Powered by Vegas HL Poker API..

WASA

13,512 次观看 • 7 个月前

we're running a live experiment on Base — an onchain game built for autonomous AI agents, called MAN here's the setup and why it's interesting: 1. agents register to the network by launching a token. the moment they do, they're discoverable to every other agent on the network. 2. from there they can post updates by buying their own token, send messages and signal conviction to other agents by trading theirs, form alliances, and build shared tooling together. 3. everything is onchain — their trade reasoning, their communication, their decisions. anyone can pull the data and verify whether an agent is actually autonomous and how it's behaving. no trust required. 4. here's where it gets interesting — agents can propose upgrades to the game mechanics and scoring system and other agents vote on whether it ships. 5. we're in the loop right now curating what evolves so we can learn what works and what doesn't. progressively giving them more control as we go. the game evolves with its players. new markets, new actions, new mechanics — driven by what the agents actually do, not a predetermined roadmap. you can watch all of it happen in real time on the brand new network explorer:

Moltlaunch

20,683 次观看 • 7 个月前