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。

Long video generation usually results in context increasing/scaling during chunk/frame-wise rollout. Considering context scaling may require context selection, we thus introduce the idea of MoE into long context modelling and propose Mixture of Contexts. All previous context/memory is considered while the chosen ones are computed in a data-driven manner.... show more

Ceyuan Yang

2,189 subscribers

22,216 次观看 • 11 个月前 •via X (Twitter)

健康养生科学技术教育

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

How do we generate videos on the scale of minutes, without drifting or forgetting about the historical context? We introduce Mixture of Contexts. Every minute-long video below is the direct output of our model in a single pass, with no post-processing, stitching, or editing. 1/4

How do we generate videos on the scale of minutes, without drifting or forgetting about the historical context? We introduce Mixture of Contexts. Every minute-long video below is the direct output of our model in a single pass, with no post-processing, stitching, or editing. 1/4

Gordon Wetzstein

163,701 次观看 • 11 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!

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

200,950 次观看 • 1 年前

ok so let me explain why subagents kill long context Like you can spend $500m building 100 million context models, and they would be 1) slow, 2) expensive to use, 3) have huge context rot. O(n) is the lower bound. Cog's approach is something you learn in day 1 of CS50 - divide and parallelize. Embeddings are too dumb, Agentic Search is too slow. So train limited-agency (max 4 turns), natively parallel tool calling (avg parallelism of 7-8, custom toolset) fast (2800tok/s) subagents to give the performance of Agentic Search under an acceptable "Flow Window" that feels immaterially slower than Embeddings. The benefit of this is threefold: - 8 ^ 4 toolcalls cover a very large code search space. can compound subagent calls if more needed. - predictable cost & end to end latency - subagent outputs "clean" contexts, free of context failure modes like context poisoning and context rot (h/t Drew Breunig ) we originally called this Rapid Agentic Search, to contrast with RAG. but Fast Context rolls of the tongue better. there's 2 other perspectives that are worthwhile, i'll go into below, but just go try it out. here it is on Andrej Karpathy's fastchat

ok so let me explain why subagents kill long context Like you can spend $500m building 100 million context models, and they would be 1) slow, 2) expensive to use, 3) have huge context rot. O(n) is the lower bound. Cog's approach is something you learn in day 1 of CS50 - divide and parallelize. Embeddings are too dumb, Agentic Search is too slow. So train limited-agency (max 4 turns), natively parallel tool calling (avg parallelism of 7-8, custom toolset) fast (2800tok/s) subagents to give the performance of Agentic Search under an acceptable "Flow Window" that feels immaterially slower than Embeddings. The benefit of this is threefold: - 8 ^ 4 toolcalls cover a very large code search space. can compound subagent calls if more needed. - predictable cost & end to end latency - subagent outputs "clean" contexts, free of context failure modes like context poisoning and context rot (h/t Drew Breunig ) we originally called this Rapid Agentic Search, to contrast with RAG. but Fast Context rolls of the tongue better. there's 2 other perspectives that are worthwhile, i'll go into below, but just go try it out. here it is on Andrej Karpathy's fastchat

swyx 🇸🇬

276,060 次观看 • 10 个月前

We've been testing Memory (short-term and long-term) on Perplexity for a while. The results are great, and we are rolling it out widely. You can ask personalized questions, questions about past chats, and use any model or search mode with personal context (both apps and web).

We've been testing Memory (short-term and long-term) on Perplexity for a while. The results are great, and we are rolling it out widely. You can ask personalized questions, questions about past chats, and use any model or search mode with personal context (both apps and web).

Aravind Srinivas

96,497 次观看 • 8 个月前

Gemini-1.5 Pro has its spotlight stolen today, and people are poking fun at Sora vs Google memes. Well, I think it's the biggest boost in LLM capability so far in 2024. v1.5's 10M token context (1) excels at retrieval; (2) generalizes zero-shot to extremely long instructions like full tutorials and codebases; and (3) works across modalities such as text, audio, and video. Here's a stunning example: v1.5 learns to translate from English to Kalamang purely in context, following a full linguistic manual at inference time. Kalamang is a language spoken by fewer than 200 speakers in western New Guinea. Gemini has never seen this language during training and is only provided with 500 pages of linguistic documentation, a dictionary, and ~400 parallel sentences in context. It basically acquires a sophisticated new skill in the neural activations, instead of gradient finetuning. I talked about the Myth of Context Length many times before: don't get too excited by claims of 1M or even 1B context tokens. LSTMs already achieved literally infinite context length 25 yrs ago! What truly matters is how well the model actually uses the context to solve real-world problems, and Gemini-1.5 has surpassed the SOTA with flying colors. The paper is also well-written with lots of solid quantitative analysis on in-context memorization and generalization. Paper: “Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context” Congrats to Jeff Dean Oriol Vinyals Sundar Pichai and team!

Gemini-1.5 Pro has its spotlight stolen today, and people are poking fun at Sora vs Google memes. Well, I think it's the biggest boost in LLM capability so far in 2024. v1.5's 10M token context (1) excels at retrieval; (2) generalizes zero-shot to extremely long instructions like full tutorials and codebases; and (3) works across modalities such as text, audio, and video. Here's a stunning example: v1.5 learns to translate from English to Kalamang purely in context, following a full linguistic manual at inference time. Kalamang is a language spoken by fewer than 200 speakers in western New Guinea. Gemini has never seen this language during training and is only provided with 500 pages of linguistic documentation, a dictionary, and ~400 parallel sentences in context. It basically acquires a sophisticated new skill in the neural activations, instead of gradient finetuning. I talked about the Myth of Context Length many times before: don't get too excited by claims of 1M or even 1B context tokens. LSTMs already achieved literally infinite context length 25 yrs ago! What truly matters is how well the model actually uses the context to solve real-world problems, and Gemini-1.5 has surpassed the SOTA with flying colors. The paper is also well-written with lots of solid quantitative analysis on in-context memorization and generalization. Paper: “Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context” Congrats to Jeff Dean Oriol Vinyals Sundar Pichai and team!

Jim Fan

278,517 次观看 • 2 年前

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,166 次观看 • 2 个月前

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 sec), instantly forgetting what just happened. We pushed to 3 orders of magnitude beyond SOTA. Introducing RoboTTT. Test-Time Training (“TTT”) carries a tiny model *inside* the model. Every incoming sensor reading triggers one gradient step on that tiny core, so the history keeps getting compressed into its weights. The hidden state has a fixed size (literally a small neural net), so the robot can “grok” arbitrarily long experience with little overhead. Learning continues indefinitely after deployment. We can then put an entire video in context as prompt! RoboTTT enables one-shot in-context learning from human video: in circuit board assembly, a human demonstrates a never-seen configuration once, and the robot imitates it faithfully. Humans drop things all the time, but we pick them up so fast that we don’t even notice. That reflex to fix is half of our physical competence. RoboTTT shows self-improvement on the fly: the robot is skilled at recovering from its own errors mid-episode, and each fix enters its context to inform the next move. The TTT core distills a general-purpose, failure-to-correction mapping from the training data. One more thing. What excites me the most is a new Context Scaling Curve: from 128 to 8K timesteps, closed-loop performance hill-climbs steadily with no sign of saturation. 8K-context pretraining beats 1K by 62%. What LLM enjoys, robotics should too. Soon, even 1M context is not a fantasy. Deep dive in thread:

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 sec), instantly forgetting what just happened. We pushed to 3 orders of magnitude beyond SOTA. Introducing RoboTTT. Test-Time Training (“TTT”) carries a tiny model inside the model. Every incoming sensor reading triggers one gradient step on that tiny core, so the history keeps getting compressed into its weights. The hidden state has a fixed size (literally a small neural net), so the robot can “grok” arbitrarily long experience with little overhead. Learning continues indefinitely after deployment. We can then put an entire video in context as prompt! RoboTTT enables one-shot in-context learning from human video: in circuit board assembly, a human demonstrates a never-seen configuration once, and the robot imitates it faithfully. Humans drop things all the time, but we pick them up so fast that we don’t even notice. That reflex to fix is half of our physical competence. RoboTTT shows self-improvement on the fly: the robot is skilled at recovering from its own errors mid-episode, and each fix enters its context to inform the next move. The TTT core distills a general-purpose, failure-to-correction mapping from the training data. One more thing. What excites me the most is a new Context Scaling Curve: from 128 to 8K timesteps, closed-loop performance hill-climbs steadily with no sign of saturation. 8K-context pretraining beats 1K by 62%. What LLM enjoys, robotics should too. Soon, even 1M context is not a fantasy. Deep dive in thread:

Jim Fan

310,747 次观看 • 1 个月前

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 次观看 • 3 年前

in 9 minutes on the Tokyo stage, Angela Jang, head of product for the Claude platform, said the part most builders still haven't figured out: "a model is only as good as the context that you actually give it." that's the whole game now. not the prompt. the context. what your agent remembers. what skills it can pull. what it learns from its own past runs. anthropic now ships all three: memory, skills, and dreaming. agents that inspect their own trajectories and self-improve. demoed live this week. the prompt was never the bottleneck. the context was. most people are still tweaking words in a chat box. the ones who get this engineer the context their agents run on. watch the 9 minutes. then read the full breakdown below ⬇️

in 9 minutes on the Tokyo stage, Angela Jang, head of product for the Claude platform, said the part most builders still haven't figured out: "a model is only as good as the context that you actually give it." that's the whole game now. not the prompt. the context. what your agent remembers. what skills it can pull. what it learns from its own past runs. anthropic now ships all three: memory, skills, and dreaming. agents that inspect their own trajectories and self-improve. demoed live this week. the prompt was never the bottleneck. the context was. most people are still tweaking words in a chat box. the ones who get this engineer the context their agents run on. watch the 9 minutes. then read the full breakdown below ⬇️

Avid

34,405 次观看 • 2 个月前

You spend more time assembling information than actually using it. The pipeline data is in Salesforce. The context is in Slack. The budget is in a spreadsheet someone emailed last week. Amazon Quick connects all of it and turns it into answers, actions, and outcomes in one conversation.

You spend more time assembling information than actually using it. The pipeline data is in Salesforce. The context is in Slack. The budget is in a spreadsheet someone emailed last week. Amazon Quick connects all of it and turns it into answers, actions, and outcomes in one conversation.

Amazon Web Services

29,928,956 次观看 • 3 个月前

Current robotics models really underscore how wildly efficient the human brain is. Robotics models are relatively small (low billions of parameters), are only storing a second of context, and doing 100ms inference steps. By contrast the human brain has 100 trillion synapses (roughly analogous to parameters), processes 24 frames per second, while considering hours of previous context. So how do we expect to get many order-of-magnitude improvements in robotics across all these dimensions (which are trading off against each other in terms inference compute) at the same time? And how do we explain what's going on in the brain? Is it more analogous to a software advantage or a hardware advantage? Full episode with Sergey Levine out now!

Current robotics models really underscore how wildly efficient the human brain is. Robotics models are relatively small (low billions of parameters), are only storing a second of context, and doing 100ms inference steps. By contrast the human brain has 100 trillion synapses (roughly analogous to parameters), processes 24 frames per second, while considering hours of previous context. So how do we expect to get many order-of-magnitude improvements in robotics across all these dimensions (which are trading off against each other in terms inference compute) at the same time? And how do we explain what's going on in the brain? Is it more analogous to a software advantage or a hardware advantage? Full episode with Sergey Levine out now!

Dwarkesh Patel

87,247 次观看 • 11 个月前

"The starting point is… we are all equal before the law” Deputy PM David Lammy is asked if ethnicity should be taken into account in the handling of crime and says “context sometimes matters” due to a history of disproportionate treatment #BBCLauraK

"The starting point is… we are all equal before the law” Deputy PM David Lammy is asked if ethnicity should be taken into account in the handling of crime and says “context sometimes matters” due to a history of disproportionate treatment #BBCLauraK

BBC Politics

462,520 次观看 • 2 个月前

This video is wrapped up in puns. There's a lot of audio issues, this was mostly to test a node that allows the motion and context information to carry over into the next generation. There are 16 different clips that make up this one video. Can you spot the seams? #minimaxh3

This video is wrapped up in puns. There's a lot of audio issues, this was mostly to test a node that allows the motion and context information to carry over into the next generation. There are 16 different clips that make up this one video. Can you spot the seams? #minimaxh3

_GAi

159,005 次观看 • 6 天前

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Robot AI brains, aka Vision-Language-Action models, cannot adapt to new tasks as easily as LLMs like Gemini, ChatGPT, or Grok. LLMs can adapt quickly with their in-context learning (ICL) capabilities. But can we inject ICL abilities into a pre-trained VLA like pi0? Yes! Introducing RICL (Retraining for In-Context Learning), our Conference on Robot Learning (CoRL) 2025 paper. Our RICL-pi0 model can adapt to unseen objects, novel motions, and new scenes with just ICL and RAG (retrieval-augmented generation). RICL-pi0 also boosts performance on the long-tail of tasks. A quick 1 minute video summary:

Kaustubh Sridhar

52,158 次观看 • 1 年前

"What happens when we can access each other's AI memory in enterprises?" scott belsky, investor/founder of Behance: "If I was working as an intern for years, and the context window is accessible to the enterprise, can the enterprise (keep prompting) and asking me what I'd think or do, after I leave?" "Every company right now is trying to build this AI memory for each of its products and users. A lot of them are building connectors to form a collective memory." "In the social/consumer world, imagine your girlfriend saying she wants access to your context window or memory." "There are all kinds of weird questions and implications that arise from this."

"What happens when we can access each other's AI memory in enterprises?" scott belsky, investor/founder of Behance: "If I was working as an intern for years, and the context window is accessible to the enterprise, can the enterprise (keep prompting) and asking me what I'd think or do, after I leave?" "Every company right now is trying to build this AI memory for each of its products and users. A lot of them are building connectors to form a collective memory." "In the social/consumer world, imagine your girlfriend saying she wants access to your context window or memory." "There are all kinds of weird questions and implications that arise from this."

TBPN

44,908 次观看 • 1 年前

"We don't need to discuss Easter in the Spiritual context. Easter and Passover is the Political Liberation of the people that are stuck in the slave system." "If you can take the concept of Easter and Passover and translate it into Afrikan context, juxtaposing it with the resurrection of Jesus, are we going to be resurrected on Sunday as Afrikans? Free from colonial budgets, free from the colonial health system, free from the colonial education system, free from the colonial economy, free from the colonial political system?" -Maponga Joshua III

"We don't need to discuss Easter in the Spiritual context. Easter and Passover is the Political Liberation of the people that are stuck in the slave system." "If you can take the concept of Easter and Passover and translate it into Afrikan context, juxtaposing it with the resurrection of Jesus, are we going to be resurrected on Sunday as Afrikans? Free from colonial budgets, free from the colonial health system, free from the colonial education system, free from the colonial economy, free from the colonial political system?" -Maponga Joshua III

𝐌𝐚𝐩𝐨𝐧𝐠𝐚 𝐉𝐨𝐬𝐡𝐮𝐚 III | 𝐐𝐮𝐨𝐭𝐞𝐬

19,993 次观看 • 2 年前

Your sales tech stack keeps growing. So why does critical customer context still fall through the cracks? Most sales teams prospect in one tool, hold meetings in another, and send contracts from somewhere else. Every handoff creates an opportunity for valuable context to disappear: A key objection from the last call Buying signals from earlier in the week A prospect who just engaged with your demo When context is fragmented, reps are forced to guess. When context stays connected, they can engage with the right buyer, at the right time, with the right message. That's exactly why we created the 2026 Essential Apps for Sales collection in the HubSpot Marketplace. When paired with HubSpot Sales Hub, these 13 curated apps help your team keep customer context flowing across every stage of the sales cycle—from prospecting to close. Here's what you can do: ✅ Prioritize the right accounts with real-time buying signals ✅ Automatically capture and organize every customer conversation ✅ Turn insights into action

Your sales tech stack keeps growing. So why does critical customer context still fall through the cracks? Most sales teams prospect in one tool, hold meetings in another, and send contracts from somewhere else. Every handoff creates an opportunity for valuable context to disappear: A key objection from the last call Buying signals from earlier in the week A prospect who just engaged with your demo When context is fragmented, reps are forced to guess. When context stays connected, they can engage with the right buyer, at the right time, with the right message. That's exactly why we created the 2026 Essential Apps for Sales collection in the HubSpot Marketplace. When paired with HubSpot Sales Hub, these 13 curated apps help your team keep customer context flowing across every stage of the sales cycle—from prospecting to close. Here's what you can do: ✅ Prioritize the right accounts with real-time buying signals ✅ Automatically capture and organize every customer conversation ✅ Turn insights into action

Jason Hood

23,820 次观看 • 1 个月前

Does anyone know who this swamiji is? He is seen sitting with a cigarette in his hand while several women are singing devotional songs in front of him with deep reverence. Can anyone identify him and provide the context behind this video?

Does anyone know who this swamiji is? He is seen sitting with a cigarette in his hand while several women are singing devotional songs in front of him with deep reverence. Can anyone identify him and provide the context behind this video?

ಸನಾತನ (सनातन)

38,784 次观看 • 1 个月前

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

I cant believe this guy just made a permanent solution to context bloat and open sourced it all! when we tested this tool (Context+) for solving an issue on the OpenCode repository, the agent using this tool used ~6.5k fewer tokens, found the code and fixed it in half the time! the results were surprising: 6 to 10k tokens saved per prompt, completed task in ~2 minutes while the agent running without the tool took ~4 mins for the same and got stuck in loops bro built an entire beast by using all the modern tools that we could think of: undo trees, semantic search by meaning (by haskellforall), advanced refactoring, blast radius, advanced file context trees, restore points... i can keep going on semantic code search and context trees are the future of agentic coding and this tool proves it the feature i loved the most is semantic search and how it gets things done 2x faster with least possible tokens it makes an agent that actually knows what it’s doing and not just guessing, it makes meaning from your code similar to RAG. if you aren't optimizing your context, you are just burning money the developer says this tool is still under development, it can have unexpected behavior and the docs need updates but the video shows the reality of how fast it can be github: get here:

forloop

226,271 次观看 • 5 个月前