正在加载视频...

视频加载失败

🚀 Memex Launch Week, Day 1! Today, we dive into our redesigned interface + two game-changing features: - Control Center: one-click version control, app start/stop, and docs. - Context Management: keep your project's memory clean and relevant as it grows. Learn more:

579,706 次观看 • 10 个月前 •via X (Twitter)

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

US to Iranian Regime: “Give up your nuclear program, give up the enriched uranium, give up your ballistic missile program, stop funding proxies and terrorism, stop killing your citizens, and just be a normal decent country” Iranian Regime to US: “Let’s compromise. Stop the war. Give us a lot of money. Release all our frozen assets. Commit to never attacking us again. And we have full control of the Strait of Hormuz. In return, we keep our nuclear program, we keep the uranium, we keep our missile program, we keep funding our proxies, we keep killing our people… oh, and death to Israel and death to America” US: “We think you misunderstood. You cannot have nukes. No uranium. You must stop killing civilians. You must stop funding proxies, and you must open the Strait of Hormuz” Iranian Regime: “Ah, now we understand. Ok then, let’s negotiate. Stop the war. Give us a lot of money. Release all our frozen assets. Commit to never attacking us again. And we have full control of the Strait of Hormuz. In return, we keep our nuclear program, we keep the uranium, we keep our missile program, we keep funding our proxies, we keep killing our people… oh, and death to Israel and death to America” US: “Listen, you either agree to our terms or we will have no choice but to strike again and all hell will break loose. You have 3 days.” Iranian Regime: “Fine. You’re twisting our arm. We know you won’t attack and if you do we will burn the whole region and humiliate you. But… we are willing to negotiate in good faith. So… Stop the war. Give us a lot of money. Release all our frozen assets. Commit to never attacking us again. And we have full control of the Strait of Hormuz. In return, we keep our nuclear program, we keep the uranium, we keep our missile program, we keep funding our proxies, we keep killing our people… oh, and death to Israel and death to America” US: “Enough. We are giving you one more last chance. Agree to our terms or else. No more chances. You have one week.” Iranian Regime: “We are prepared to negotiate and meet you half way. It has to be fair. So… Stop the war. Give us a lot of money. Release all our frozen assets. Commit to never attacking us again. And we have full control of the Strait of Hormuz. In return, we keep our nuclear program, we keep the uranium, we keep our missile program, we keep funding our proxies, we keep killing our people… oh, and death to Israel and death to America” US: “Stop playing games. This is serious. We will not give you any more chances. You have two weeks or all hell will break loose” Iranian Regime: “We accept to agree to negotiate where we can discuss your terms over the next 30 days. But… Stop the war. Give us a lot of money. Release all our frozen assets. Commit to never attacking us again. And we have full control of the Strait of Hormuz. In return, we keep our nuclear program, we keep the uranium, we keep our missile program, we keep funding our proxies, we keep killing our people… oh, and death to Israel and death to America” And round and round and round we go. Dear President Trump. There is only one way to negotiate with the Islamic regime or any Islamic terrorists. Just one way👇🏼 President Donald J. Trump Secretary of War Pete Hegseth

Mor Edge Insight

29,686 次观看 • 1 个月前

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,752 次观看 • 1 年前