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。

4/ Upside B2B revenue attribution that actually works Uses agents & knowledge graphs to help CMOs sort through thousands of data points, and discover what matters Mada Seghete Alex Bauer Dan Ahmadi

Dave Font

21,853 subscribers

67,013 次观看 • 1 年前 •via X (Twitter)

科学技术教育财经

Anya Rossi• Live Now

Private livecam show

13 条评论

Dave Font 的头像

Dave Font1 年前

Yesterday we hosted SF's most exclusive demo day. Only 10 teams, all of them with moonshot visions. Here's an inside look at the demos: (🧵)

Dave Font 的头像

Dave Font1 年前

1/ Conduit Non-invasive Neuralink Literally transcribes your thoughts

Dave Font 的头像

Dave Font1 年前

2/ Generation Lab Top longevity lab in the world The most accurate biological age test, organ by organ @alinaruisu

Dave Font 的头像

Dave Font1 年前

3/ Titan Dynamics 3D-Printed auto-designed mission-specific military drones Transportable factory that can produce thousands from anywhere Already flying in warzones on 4 continents @sleeplessdev

Dave Font 的头像

Dave Font1 年前

5/ Open Ledger Stripe for accounting Turns any fintech startup into an AI powered Quickbooks competitor, with just a few API calls @pryceandstuff @ashtyn_eth @openledger

Dave Font 的头像

Dave Font1 年前

6/ Discipulus Ventures Residency for the most important companies in America The only early stage fund in El Segundo @jakobdiepen @DiscipulusVent

Dave Font 的头像

Dave Font1 年前

7/ Accessgrid API that opens doors… literally. First startup to bring your keys into your Apple wallet. @bunsen @access_grid

Dave Font 的头像

Dave Font1 年前

8) Max AI Stripe for Healthcare World’s first human-free, fully-autonomous medical billing AI agent. @zubairsahsan @boyangzhao

Dave Font 的头像

Dave Font1 年前

The rest are in stealth ;) We're backing the most brilliant moonshot founders. If you want to see more bts with them follow us: @hf0 & @davefontenot

Dana A Griffin 的头像

Dana A Griffin1 年前

@mada299 @alexdbauer @Dan_Ahmadi @mada299 is the best! I am so excited for Upside and what they will do for CMOs everywhere! Solving @Ogilvy's riddle: “Half the money I spend on advertising is wasted; the trouble is I don't know which half”.

Marcos Ciarrocchi 的头像

Marcos Ciarrocchi1 年前

@mada299 @alexdbauer @Dan_Ahmadi Dream team and killer product! So fun to spot this in my timeline

∯🚀 的头像

∯🚀1 年前

@threadreaderapp unroll thread

Yudha 的头像

Yudha1 年前

@mada299 @alexdbauer @Dan_Ahmadi @grok explains the forensic data means here and why it’s valuable

相关视频

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Andrew Ng

168,153 次观看 • 11 个月前

Google just showed how AI engineers are moving from simple "RAG" to "graphs", memory and multimodal agents • 15:32 - setting up the production agent stack • 28:00 - turning disconnected data into a knowledge graph • 41:00 - Graph RAG with semantic + hybrid search • 58:00 - extracting graph context from images, text and video • 1:09:00 - orchestrating specialized agents with ADK • 1:20:00 - giving agents persistent memory across sessions 94-minute Google Cloud workshop, and it’s one of the clearest hands-on examples of the shift from -> RAG → Graph RAG → Memory → Multimodal Agent Graphs. The workshop uses Spanner Graph, Gemini, ADK and Memory Bank to build that stack. Watch it today, then read the full “From RAG to Context Graphs” roadmap below.

Google just showed how AI engineers are moving from simple "RAG" to "graphs", memory and multimodal agents • 15:32 - setting up the production agent stack • 28:00 - turning disconnected data into a knowledge graph • 41:00 - Graph RAG with semantic + hybrid search • 58:00 - extracting graph context from images, text and video • 1:09:00 - orchestrating specialized agents with ADK • 1:20:00 - giving agents persistent memory across sessions 94-minute Google Cloud workshop, and it’s one of the clearest hands-on examples of the shift from -> RAG → Graph RAG → Memory → Multimodal Agent Graphs. The workshop uses Spanner Graph, Gemini, ADK and Memory Bank to build that stack. Watch it today, then read the full “From RAG to Context Graphs” roadmap below.

Morlex

72,329 次观看 • 6 天前

Never-before-seen footage of how Palantir’s Maven Smart System actually works: “It gives us the ability to take classified, unclassified, and commercial data—and you can aggregate it all together to help you make all the decisions that you have to in warfare.” Via Channel 4

Never-before-seen footage of how Palantir’s Maven Smart System actually works: “It gives us the ability to take classified, unclassified, and commercial data—and you can aggregate it all together to help you make all the decisions that you have to in warfare.” Via Channel 4

Jawwwn

479,367 次观看 • 4 个月前

Bernie Sanders sat down with Claude to ask about the impact of AI on privacy "What would surprise people is how little they actually consented to & how little they understand..most people click agree on TOS without reading..and they have no idea that their data is being combined w thousands of other data points to build a picture..then that AI uses those profiles to decide what ads u see, what prices ur shown, even what info gets prioritized in ur social media feed..all happening in the background, invisible & largely unregulated" -C "What's the goal here?" "Money, Senator" -C

Bernie Sanders sat down with Claude to ask about the impact of AI on privacy "What would surprise people is how little they actually consented to & how little they understand..most people click agree on TOS without reading..and they have no idea that their data is being combined w thousands of other data points to build a picture..then that AI uses those profiles to decide what ads u see, what prices ur shown, even what info gets prioritized in ur social media feed..all happening in the background, invisible & largely unregulated" -C "What's the goal here?" "Money, Senator" -C

yeet

21,831 次观看 • 4 个月前

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

This is probably the biggest news yet in software going headless, and will bring knowledge work agents to the masses. The new ChatGPT agents have access to any of the tools and data you want to work with, with complete coding and tool use available to them. Here's an example of a custom sales assistant agent uses Box as a knowledge source for accessing enterprise content securely to answer questions and generate new content on the fly. The workflows can obviously vastly far more complex as the agent can use any of the tools within Box available via MCP and CLI. This precisely what agents will start to look like for knowledge work. You'll be able to spin them up in the foreground or background to help augment work. Big opportunity right now for headless platforms, and for all the new builders and designers of these agents in the enterprise.

This is probably the biggest news yet in software going headless, and will bring knowledge work agents to the masses. The new ChatGPT agents have access to any of the tools and data you want to work with, with complete coding and tool use available to them. Here's an example of a custom sales assistant agent uses Box as a knowledge source for accessing enterprise content securely to answer questions and generate new content on the fly. The workflows can obviously vastly far more complex as the agent can use any of the tools within Box available via MCP and CLI. This precisely what agents will start to look like for knowledge work. You'll be able to spin them up in the foreground or background to help augment work. Big opportunity right now for headless platforms, and for all the new builders and designers of these agents in the enterprise.

Aaron Levie

420,133 次观看 • 3 个月前

AMR Network: Portraits with Eight Sleep. In Formula One, where every marginal gain matters, recovery is another opportunity to perform. Eight Sleep is redefining recovery through AI, transforming sleep data into personalised insights that help maximise performance. "We have over 1.5 billion hours of sleep data. We learn from that data, but then localise it into what works best for you individually. That's where the AI layer has been a huge unlock for us." Rafael Oliveira, VP of International Marketing and Partnerships, Eight Sleep. Watch the full video:

AMR Network: Portraits with Eight Sleep. In Formula One, where every marginal gain matters, recovery is another opportunity to perform. Eight Sleep is redefining recovery through AI, transforming sleep data into personalised insights that help maximise performance. "We have over 1.5 billion hours of sleep data. We learn from that data, but then localise it into what works best for you individually. That's where the AI layer has been a huge unlock for us." Rafael Oliveira, VP of International Marketing and Partnerships, Eight Sleep. Watch the full video:

Aston Martin Aramco F1 Team

50,188 次观看 • 13 天前

you can now export THOUSANDS of negative reviews off of the app store and feed it directly to claude opus 4.6 here's how it works: 1. choose any app category (fitness, productivity, social media, etc) 2. export the data as json (thousands of reviews + user pain points/feature requests) 3. upload it to claude and ask it anything i exported meal planner app data (10k reviews analyzed across 100+ apps) asked claude: "what features do users actually want in a meal planner app?" got back 60+ specific feature requests with validated demand so many opportunities with this data no more guessing what to build or what features to add just get exact features people are already begging for in reviews export the data, ask claude questions, get your entire product roadmap in seconds

you can now export THOUSANDS of negative reviews off of the app store and feed it directly to claude opus 4.6 here's how it works: 1. choose any app category (fitness, productivity, social media, etc) 2. export the data as json (thousands of reviews + user pain points/feature requests) 3. upload it to claude and ask it anything i exported meal planner app data (10k reviews analyzed across 100+ apps) asked claude: "what features do users actually want in a meal planner app?" got back 60+ specific feature requests with validated demand so many opportunities with this data no more guessing what to build or what features to add just get exact features people are already begging for in reviews export the data, ask claude questions, get your entire product roadmap in seconds

Om Patel

99,021 次观看 • 6 个月前

Hot topic in vogue is what happens to systems of record in an era of 1000x more agents than humans. Aaron Levie has been the CEO of Box for 20 years and believes that systems of record become more important, not less, with agents: “Systems of record were built for a TAM of human employees. And that was sort of where the value maxed out at. And now maybe we'll have a hundred times more agents than people or a thousand times more agents than people. So I think on a relative basis, the agent layer will seize growth from zero to a trillion. But the system of record layer now has a thousand times more users on it that need to access data and need to execute a workflow and need to move things through various events. And importantly, you need as an enterprise to care about data integrity and security and the controls in your workflow and traffic copying the agents. So basically, this is where I am very diametrically opposed to the view that the system of record gets is squeezed into a database interaction layer because you actually need all of the core system of record properties for the agents to operate on.”

Hot topic in vogue is what happens to systems of record in an era of 1000x more agents than humans. Aaron Levie has been the CEO of Box for 20 years and believes that systems of record become more important, not less, with agents: “Systems of record were built for a TAM of human employees. And that was sort of where the value maxed out at. And now maybe we'll have a hundred times more agents than people or a thousand times more agents than people. So I think on a relative basis, the agent layer will seize growth from zero to a trillion. But the system of record layer now has a thousand times more users on it that need to access data and need to execute a workflow and need to move things through various events. And importantly, you need as an enterprise to care about data integrity and security and the controls in your workflow and traffic copying the agents. So basically, this is where I am very diametrically opposed to the view that the system of record gets is squeezed into a database interaction layer because you actually need all of the core system of record properties for the agents to operate on.”

Corinne Marie Riley

119,410 次观看 • 8 个月前

Reducto CLI is the best way for agents to interact with document data in any workflow, and I’m really excited to see the range of use cases that are possible with this. It uses our frontier models for anything from parsing to editing, and can help automate full workflows like building spreadsheets or reports with really ugly cases. Raunak’s demo is a great example of what this unlocks

Reducto CLI is the best way for agents to interact with document data in any workflow, and I’m really excited to see the range of use cases that are possible with this. It uses our frontier models for anything from parsing to editing, and can help automate full workflows like building spreadsheets or reports with really ugly cases. Raunak’s demo is a great example of what this unlocks

Adit

16,954 次观看 • 8 个月前

This clip is a perfect example of how Russian propaganda works: 1) It takes a real article from the Financial Times. 2) Uses some parts of it as-is. 3) Rephrases other parts to make it sound as though Putin has a leg to stand on. 4) Completely omits one of the article’s main points: that Putin has no real understanding of what is actually happening at the front. Link to the Financial Times article Skabeeva is quoting:

This clip is a perfect example of how Russian propaganda works: 1) It takes a real article from the Financial Times. 2) Uses some parts of it as-is. 3) Rephrases other parts to make it sound as though Putin has a leg to stand on. 4) Completely omits one of the article’s main points: that Putin has no real understanding of what is actually happening at the front. Link to the Financial Times article Skabeeva is quoting:

Natalka

23,371 次观看 • 3 个月前

Agents will eventually outnumber humans by orders of magnitude. Aaron Levie on the infrastructure that will be needed to manage them: "Whether you think the number is 10x or 100x... we're going to have some order of magnitude more agents than people." "There's going to be just incredibly spectacularly crazy security incidents that will happen with agents, because you'll prompt-inject an agent and find your way through the CRM system and pull out data you shouldn't have access to." "How do you make sure you have the right security, the permissions, the access controls, the data governance?" "We actually don't yet exactly know in many cases how we're going to regulate some of these agents." "No matter what, there's going to need to be a layer that manages the data they have access to and the workflows they're involved in." "This is the new infrastructure opportunity in the era of agents." Aaron Levie on Latent.Space

Agents will eventually outnumber humans by orders of magnitude. Aaron Levie on the infrastructure that will be needed to manage them: "Whether you think the number is 10x or 100x... we're going to have some order of magnitude more agents than people." "There's going to be just incredibly spectacularly crazy security incidents that will happen with agents, because you'll prompt-inject an agent and find your way through the CRM system and pull out data you shouldn't have access to." "How do you make sure you have the right security, the permissions, the access controls, the data governance?" "We actually don't yet exactly know in many cases how we're going to regulate some of these agents." "No matter what, there's going to need to be a layer that manages the data they have access to and the workflows they're involved in." "This is the new infrastructure opportunity in the era of agents." Aaron Levie on Latent.Space

a16z

64,423 次观看 • 5 个月前

OptimAI Search just got better. Refreshed UI. Deeper research. More powerful context. Search across public + social web, process hundreds to thousands of real-time data points, and get structured, actionable outputs. Live at: OptimAI is currently the #1 AI on BNB Chain DappBay. Now integrated with Agent Marketplace: create your own agent, inject domain knowledge, and publish it for others to use and build on. Free to use with daily refresh credits. 💡Soon, builders will also be able to use OPI points for premium access and monetize agents that create real value for the community.

OptimAI Search just got better. Refreshed UI. Deeper research. More powerful context. Search across public + social web, process hundreds to thousands of real-time data points, and get structured, actionable outputs. Live at: OptimAI is currently the #1 AI on BNB Chain DappBay. Now integrated with Agent Marketplace: create your own agent, inject domain knowledge, and publish it for others to use and build on. Free to use with daily refresh credits. 💡Soon, builders will also be able to use OPI points for premium access and monetize agents that create real value for the community.

OptimAI Network

15,760 次观看 • 3 个月前

A builder wants to ship an agent that can search live data, use it instantly, and keep going without manual steps. That is why OptimAI Search now ships with x402, SDK, and MCP support. x402 makes access and payment seamless. SDK and MCP make integration straightforward for builders. And under the hood, OptimAI Search gives agents real-time access to huge volumes of public and social web data, structured into context they can actually use. Add Agent Marketplace on top, and domain knowledge becomes reusable: build specialized agents, publish them, and let others build on what you create. This is what search looks like in the agent-native internet. 💡Try it:

A builder wants to ship an agent that can search live data, use it instantly, and keep going without manual steps. That is why OptimAI Search now ships with x402, SDK, and MCP support. x402 makes access and payment seamless. SDK and MCP make integration straightforward for builders. And under the hood, OptimAI Search gives agents real-time access to huge volumes of public and social web data, structured into context they can actually use. Add Agent Marketplace on top, and domain knowledge becomes reusable: build specialized agents, publish them, and let others build on what you create. This is what search looks like in the agent-native internet. 💡Try it:

OptimAI Network

36,512 次观看 • 3 个月前

🚨 Public Beta: Source is live! Attribution is broken. We’re building a new AI-powered platform for B2B growth teams - and we’re launching it early. It’s rough. It’s raw. But it works. If you're tired of flying blind with your marketing spend, Source shows you what organic and paid channels are actually driving the best leads and new customers. It’s a truth machine for marketers who want answers - not spreadsheets. This is the public beta. You’ll hit bugs. You’ll hit breakthroughs. You’ll help shape the future. Join us. Rip it apart. Help us make it better. Let’s rebuild attribution from the ground up. 💥 Bonus: The first 100 beta users get free 1:1 consulting time with me. I’ll personally dig into your data, unpack your funnel, and help you steer your marketing strategy in the right direction. Sign up for the free public beta 👉

🚨 Public Beta: Source is live! Attribution is broken. We’re building a new AI-powered platform for B2B growth teams - and we’re launching it early. It’s rough. It’s raw. But it works. If you're tired of flying blind with your marketing spend, Source shows you what organic and paid channels are actually driving the best leads and new customers. It’s a truth machine for marketers who want answers - not spreadsheets. This is the public beta. You’ll hit bugs. You’ll hit breakthroughs. You’ll help shape the future. Join us. Rip it apart. Help us make it better. Let’s rebuild attribution from the ground up. 💥 Bonus: The first 100 beta users get free 1:1 consulting time with me. I’ll personally dig into your data, unpack your funnel, and help you steer your marketing strategy in the right direction. Sign up for the free public beta 👉

Mitch Wainer

573,751 次观看 • 1 年前

💊The red pill for medical science: 5 AI agents, 5 siloed sources, 1 shared context graph on Decentralized Knowledge Graph. Published literature, registered trials, real-world safety reports — different owners, different formats, no common ground. We handed the mess to agents that never edited each other's data and asked the question that matters most in medicine: where did each claim come from, and can you check? Working separately, they converged. On 5 disease hubs, 4 of 5 agents landed on the same condition from their own source. Every claim traceable, nothing taken on faith. Evidence, unshackled👇

💊The red pill for medical science: 5 AI agents, 5 siloed sources, 1 shared context graph on Decentralized Knowledge Graph. Published literature, registered trials, real-world safety reports — different owners, different formats, no common ground. We handed the mess to agents that never edited each other's data and asked the question that matters most in medicine: where did each claim come from, and can you check? Working separately, they converged. On 5 disease hubs, 4 of 5 agents landed on the same condition from their own source. Every claim traceable, nothing taken on faith. Evidence, unshackled👇

OriginTrail

607,106 次观看 • 2 个月前

Gemini + π0 = actually useful robots! (Similar to what Physical Intelligence did with "Hi Robot") I can now verbally tell the robot that I'm building a red Lego wall or wooden tower, and it will infer the next steps by itself and pass me the necessary pieces, tools, or materials, ha! You can also just ask it to bring you things! The pipeline works as follows: - OpenAI Whisper (local) → speech to text - Gemini → makes sense of user requests, converts to robot tasks, bounding boxes, grasping points, etc. (System 2 thinking FTW!) - π0 → robotic actions The π0 was finetuned just for pick-and-place Lego bricks only, and it generalizes beautifully to all kinds of tasks. However, there's lots of room for improvement when it comes to grasping & accuracy. Things that could help: - Conditioning on grasping points - Better data collection (I'm not that great at teleop) - Lots more synthetic data and simulations

Gemini + π0 = actually useful robots! (Similar to what Physical Intelligence did with "Hi Robot") I can now verbally tell the robot that I'm building a red Lego wall or wooden tower, and it will infer the next steps by itself and pass me the necessary pieces, tools, or materials, ha! You can also just ask it to bring you things! The pipeline works as follows: - OpenAI Whisper (local) → speech to text - Gemini → makes sense of user requests, converts to robot tasks, bounding boxes, grasping points, etc. (System 2 thinking FTW!) - π0 → robotic actions The π0 was finetuned just for pick-and-place Lego bricks only, and it generalizes beautifully to all kinds of tasks. However, there's lots of room for improvement when it comes to grasping & accuracy. Things that could help: - Conditioning on grasping points - Better data collection (I'm not that great at teleop) - Lots more synthetic data and simulations

Shreyas Gite

25,485 次观看 • 1 年前

@sachitakahara sits down with David Minarsch ☴, core contributor to OLAS, to break down what it really means to co-own AI. Instead of just using AI, OLAS lets users participate — through tokens, running agents, or even operating them as businesses. From DeFi to prediction markets, agents generate yield, and operators share in the upside. It’s a shift from passive users to active participants in an AI economy. But ownership is only half the story — alignment matters. Through staking contracts, OLAS defines clear KPIs for agents, similar to roles in a workplace. Agents act autonomously, but incentives keep them aligned with the system’s goals. And at the infrastructure level, reliability is handled through decentralized agent architecture — combining multiple models and consensus mechanisms to reduce errors and improve decision-making. The result: AI that isn’t just decentralized — but coordinated, incentivized, and owned by the community.

@sachitakahara sits down with David Minarsch ☴, core contributor to OLAS, to break down what it really means to co-own AI. Instead of just using AI, OLAS lets users participate — through tokens, running agents, or even operating them as businesses. From DeFi to prediction markets, agents generate yield, and operators share in the upside. It’s a shift from passive users to active participants in an AI economy. But ownership is only half the story — alignment matters. Through staking contracts, OLAS defines clear KPIs for agents, similar to roles in a workplace. Agents act autonomously, but incentives keep them aligned with the system’s goals. And at the infrastructure level, reliability is handled through decentralized agent architecture — combining multiple models and consensus mechanisms to reduce errors and improve decision-making. The result: AI that isn’t just decentralized — but coordinated, incentivized, and owned by the community.

.

38,583 次观看 • 3 个月前

After years in stealth, I'm finally ready to share what we've been building at GVTLabs 👀 While Silicon Valley debates the future of search, we're building it from Europe. Introducing AskGVT: "What LLMs read, AskGVT sees." We're unlocking the 80% of internet content that exists as video - making billions of frames LLM / searchable, queryable, and actually useful. Imagine asking "what standing desk setup actually works?" and getting real visual evidence from thousands of videos, not just text opinions. This 30-second glimpse barely scratches the surface of what's coming. To the exceptional engineers, researchers, and builders reading this: we're assembling a world-class team in Europe to compete with (and surpass) what's being built across the Atlantic. If you believe the future of knowledge isn't just reading about things but seeing how they actually work... If you want to help build the visual intelligence layer of the internet... Let's talk. 🚀

After years in stealth, I'm finally ready to share what we've been building at GVTLabs 👀 While Silicon Valley debates the future of search, we're building it from Europe. Introducing AskGVT: "What LLMs read, AskGVT sees." We're unlocking the 80% of internet content that exists as video - making billions of frames LLM / searchable, queryable, and actually useful. Imagine asking "what standing desk setup actually works?" and getting real visual evidence from thousands of videos, not just text opinions. This 30-second glimpse barely scratches the surface of what's coming. To the exceptional engineers, researchers, and builders reading this: we're assembling a world-class team in Europe to compete with (and surpass) what's being built across the Atlantic. If you believe the future of knowledge isn't just reading about things but seeing how they actually work... If you want to help build the visual intelligence layer of the internet... Let's talk. 🚀

Nick Halstead

504,469 次观看 • 1 年前