Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Ken Levine talks about how Ghost Story Games uses Gemini to help with: - summarizing scripts - finding root cause in bug logs - analyzing the player’s telemetry data - building queryable design document database He’s skeptical on the generative side of Al: (1/2)

Sinnoware 🔶 Immersive Sim

5,136 subscribers

53,179 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Alan Wake 2 Alan Wake 2 musical was possibly the best that happened in games and Sam Lake talks about how this idea came to be with the help of @PoetsOfTheFall and how it was inspired by John Cena Peacemaker on HBO Max music Watch the full video : #BehindTheVoice #AlanWake2

Alan Wake 2 Alan Wake 2 musical was possibly the best that happened in games and Sam Lake talks about how this idea came to be with the help of @PoetsOfTheFall and how it was inspired by John Cena Peacemaker on HBO Max music Watch the full video : #BehindTheVoice #AlanWake2

Abhi Jha 🎙️

43,041 views • 2 years ago

How do you stop one customer from seeing another customer's data when they're all on the same database? I've been building SmartFarmAI in Rust farms from 550 to 60,000 birds all sharing one PostgreSQL database. This is the full breakdown: → Schema design with composite foreign keys → PostgreSQL Row-Level Security policies → Actix-web middleware for per-request tenant context → The connection pool bug that causes silent data leaks → Why my background worker processed zero events for hours 22 min. Full code walkthrough

How do you stop one customer from seeing another customer's data when they're all on the same database? I've been building SmartFarmAI in Rust farms from 550 to 60,000 birds all sharing one PostgreSQL database. This is the full breakdown: → Schema design with composite foreign keys → PostgreSQL Row-Level Security policies → Actix-web middleware for per-request tenant context → The connection pool bug that causes silent data leaks → Why my background worker processed zero events for hours 22 min. Full code walkthrough

chinedu🦀

13,481 views • 6 months ago

everybody talks about building AI chatbots, but nobody tells you HOW to do it that's why I made a full practical walkthrough on how to build an AI chatbot that's hooked up to your own custom knowledgebase inside of the walk-through i go over: – data collection: gathering all relevant documents, conversations, and info - preprocessing: cleaning up and formatting the collected data - chunking: break down the cleaned data into smaller, manageable pieces - embedding & storing in a vector database - RAG & chatbot integration: using RAG to allow the chatbot to retrieve relevant information from the vector database based on a user's question reply to this tweet w/ the word “RAG” & I’ll send it to you (must be following so I can DM)

everybody talks about building AI chatbots, but nobody tells you HOW to do it that's why I made a full practical walkthrough on how to build an AI chatbot that's hooked up to your own custom knowledgebase inside of the walk-through i go over: – data collection: gathering all relevant documents, conversations, and info - preprocessing: cleaning up and formatting the collected data - chunking: break down the cleaned data into smaller, manageable pieces - embedding & storing in a vector database - RAG & chatbot integration: using RAG to allow the chatbot to retrieve relevant information from the vector database based on a user's question reply to this tweet w/ the word “RAG” & I’ll send it to you (must be following so I can DM)

Tyler

83,616 views • 1 year ago

“Football is to recognise and anticipate on patterns. You see all kinds of patterns when you’re little…and you anticipate on the patterns…” Ruud Gullit 1. He’s seen it over and over (paying attention to the detail in his playing environment) 2. He’s made sense of what he’s seen and remembered it (thought about it to make meaning of it and processed it in both a visual and semantic way) 3. He can then make quicker and more effective decisions in games based upon what he sees in the moment (knowledge-in the game) with relation to what he’s seen and what he’s made sense of in the past (knowledge-of the game) Mastery of anticipation and decision-making… This requires… 1. Coach session design setting problems for players to detect and to solve 2. Coach behaviours that orient players’ attention to the problems to help them think about, work on, solve, and remember in-game problems 3. Player participation - attention, involvement, reflection-in-action, post session reflection-in-action to consolidate memories It’s a coach-player responsibility…

“Football is to recognise and anticipate on patterns. You see all kinds of patterns when you’re little…and you anticipate on the patterns…” Ruud Gullit 1. He’s seen it over and over (paying attention to the detail in his playing environment) 2. He’s made sense of what he’s seen and remembered it (thought about it to make meaning of it and processed it in both a visual and semantic way) 3. He can then make quicker and more effective decisions in games based upon what he sees in the moment (knowledge-in the game) with relation to what he’s seen and what he’s made sense of in the past (knowledge-of the game) Mastery of anticipation and decision-making… This requires… 1. Coach session design setting problems for players to detect and to solve 2. Coach behaviours that orient players’ attention to the problems to help them think about, work on, solve, and remember in-game problems 3. Player participation - attention, involvement, reflection-in-action, post session reflection-in-action to consolidate memories It’s a coach-player responsibility…

Daniel Abrahams

45,204 views • 2 years ago

This week on the ABCA Podcast, 2025 ABCA/Soldier Sports NAIA Assistant Coach of the Year Justin Barber of Taylor University discusses the race to two strikes: using data to help pitchers understand the difference between being in a 2-1 count versus a 1-2 count and building a staff identity around attacking early, getting to two strikes and putting pitchers in position to control the at-bat. It’s a great example of how Barber blends data with simple, repeatable concepts that players can understand and execute. 🎧 Listen to the full episode now:

This week on the ABCA Podcast, 2025 ABCA/Soldier Sports NAIA Assistant Coach of the Year Justin Barber of Taylor University discusses the race to two strikes: using data to help pitchers understand the difference between being in a 2-1 count versus a 1-2 count and building a staff identity around attacking early, getting to two strikes and putting pitchers in position to control the at-bat. It’s a great example of how Barber blends data with simple, repeatable concepts that players can understand and execute. 🎧 Listen to the full episode now:

ABCA

18,939 views • 1 month ago

“Over the weekend there were not one, not two, but three stories about Ken Martin, the chair of the DNC. He threw a phone, allegedly, and took out a mortgage on the building,” says Mark Halperin. “He’s afraid of leaking. He’s paranoid. There’s nothing more damaging for somebody in a story about how much they hate leaks, that has more leaks in it… It’s hugely important because it’s occupying the Democrats. And it’s an extraordinary act to have all this leaking, to try to get the guy to go less than 100 days before the midterms.” Ken Martin Democrats L A R R Y Kevin Walling 2WAY

“Over the weekend there were not one, not two, but three stories about Ken Martin, the chair of the DNC. He threw a phone, allegedly, and took out a mortgage on the building,” says Mark Halperin. “He’s afraid of leaking. He’s paranoid. There’s nothing more damaging for somebody in a story about how much they hate leaks, that has more leaks in it… It’s hugely important because it’s occupying the Democrats. And it’s an extraordinary act to have all this leaking, to try to get the guy to go less than 100 days before the midterms.” Ken Martin Democrats L A R R Y Kevin Walling 2WAY

2WAY

17,507 views • 1 month ago

🚨 BREAKING: Big day for voice AI. Cartesia just dropped Sonic 3.5 and Sarvam announced their $300M Series B - so I decided to put both to the test myself. Same scripts, side by side. The results are kind of insane. Sonic came out a leap ahead on emotion, alphanumerics, and switching across Indian languages mid-sentence. Karan Goel grew up in Delhi, went to IIT Delhi, and constantly talks about how much he cares about building for India. Hard to argue he doesn't mean it 👇

🚨 BREAKING: Big day for voice AI. Cartesia just dropped Sonic 3.5 and Sarvam announced their $300M Series B - so I decided to put both to the test myself. Same scripts, side by side. The results are kind of insane. Sonic came out a leap ahead on emotion, alphanumerics, and switching across Indian languages mid-sentence. Karan Goel grew up in Delhi, went to IIT Delhi, and constantly talks about how much he cares about building for India. Hard to argue he doesn't mean it 👇

Aakash Kanojiya

707,944 views • 3 months ago

Yes here is my 10 minute breathless rant about why I'm so excited about Notion Workers + Custom Agents... Context: I spent this afternoon building a custom agent to help me manage Shiori (a side project I shipped last weekend). I gave the custom agent everything it needs to understand what's happening in my product (email, log drain, sentry alerts, stripe payments, etc) and to do work on my behalf (access to coding agents). In an afternoon of tinkering, this agent can: - Diagnose bug reports proactively by looking through past email conversations, system logs, and database records - Draft replies to user questions with the correct answer based on past email threads, or help me proactively reach out to churning paid users - Self-construct a database of feature requests with an understanding of who is requesting the feature and how they're using the product today - Answer any question I have about how people use the app and what I should be thinking about next - Initiate Claude Code workflows to open PRs proactively in the background when someone sends a bug report or feature request This custom agent is now my "Side Project Chief of Staff" (I don't really know what a chief of staff does but this sounds right). I didn't write a single line of the worker code because I didn't need to: models are so good that I can link to the Workers readme, yap my desired outcome into a microphone, and I get a super-personal and highly-capable AI agent out the other side. So fucking cool. The future is now! I'm excited to see what everyone makes.

Yes here is my 10 minute breathless rant about why I'm so excited about Notion Workers + Custom Agents... Context: I spent this afternoon building a custom agent to help me manage Shiori (a side project I shipped last weekend). I gave the custom agent everything it needs to understand what's happening in my product (email, log drain, sentry alerts, stripe payments, etc) and to do work on my behalf (access to coding agents). In an afternoon of tinkering, this agent can: - Diagnose bug reports proactively by looking through past email conversations, system logs, and database records - Draft replies to user questions with the correct answer based on past email threads, or help me proactively reach out to churning paid users - Self-construct a database of feature requests with an understanding of who is requesting the feature and how they're using the product today - Answer any question I have about how people use the app and what I should be thinking about next - Initiate Claude Code workflows to open PRs proactively in the background when someone sends a bug report or feature request This custom agent is now my "Side Project Chief of Staff" (I don't really know what a chief of staff does but this sounds right). I didn't write a single line of the worker code because I didn't need to: models are so good that I can link to the Workers readme, yap my desired outcome into a microphone, and I get a super-personal and highly-capable AI agent out the other side. So fucking cool. The future is now! I'm excited to see what everyone makes.

Brian Lovin

181,875 views • 7 months ago

Our #GhostRiders completed another lunar orbit maneuver with a 3 minute, 18 second burn early this morning. This maneuver moved the lander from a high elliptical orbit to a much lower elliptical orbit around the Moon. Shortly after the burn, Blue Ghost captured incredible footage of the Moon's far side, about 120 km above the surface. In this orbit, the team will experience planned rolling comms blackouts as Blue Ghost goes around the far side of the Moon. When on the near side, the team will continue to downlink data and finalize the plan for our next maneuver that will get Blue Ghost even closer to the lunar surface and keep us right on track for landing on March 2. #BGM1

Our #GhostRiders completed another lunar orbit maneuver with a 3 minute, 18 second burn early this morning. This maneuver moved the lander from a high elliptical orbit to a much lower elliptical orbit around the Moon. Shortly after the burn, Blue Ghost captured incredible footage of the Moon's far side, about 120 km above the surface. In this orbit, the team will experience planned rolling comms blackouts as Blue Ghost goes around the far side of the Moon. When on the near side, the team will continue to downlink data and finalize the plan for our next maneuver that will get Blue Ghost even closer to the lunar surface and keep us right on track for landing on March 2. #BGM1

Firefly Aerospace

319,148 views • 1 year ago

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Santiago

40,627 views • 1 year ago

I sat down with rising star West Virginia defensive coordinator Zac Alley. We talked about his defensive philosophy, the culture he’s building on that side of the ball, and what he looks for when recruiting players to West Virginia. We also talked about how he got his start in coaching, the coaches who influenced him most, and why he decided to join Rich Rodriguez in Morgantown. This is how Zac Alley plans to help bring West Virginia back to national prominence. OUT NOW!!

I sat down with rising star West Virginia defensive coordinator Zac Alley. We talked about his defensive philosophy, the culture he’s building on that side of the ball, and what he looks for when recruiting players to West Virginia. We also talked about how he got his start in coaching, the coaches who influenced him most, and why he decided to join Rich Rodriguez in Morgantown. This is how Zac Alley plans to help bring West Virginia back to national prominence. OUT NOW!!

Adam Breneman

10,593 views • 3 months ago

How does an AI model actually learn to see? 🤖 Learn about the tech behind native multimodality, how models reason over visual data like documents and video, and the future of proactive AI assistants with Logan Kilpatrick and Gemini Model Behavior Product Lead, Ani Baddepudi. ↓ Timestamps: 01:12 Why Gemini is natively multimodal 02:23 The technology behind multimodal models 05:15 Video understanding with Gemini 2.5 09:25 Deciding what to build next 13:23 Building new product experiences with multimodal AI 17:15 The vision for proactive assistants 24:13 Improving video usability with variable FPS and frame tokenization 27:35 What’s next for Gemini’s multimodal development 31:47 Deep dive on Gemini’s document understanding capabilities 37:56 The teamwork and collaboration behind Gemini 40:56 What’s next with model behavior

How does an AI model actually learn to see? 🤖 Learn about the tech behind native multimodality, how models reason over visual data like documents and video, and the future of proactive AI assistants with Logan Kilpatrick and Gemini Model Behavior Product Lead, Ani Baddepudi. ↓ Timestamps: 01:12 Why Gemini is natively multimodal 02:23 The technology behind multimodal models 05:15 Video understanding with Gemini 2.5 09:25 Deciding what to build next 13:23 Building new product experiences with multimodal AI 17:15 The vision for proactive assistants 24:13 Improving video usability with variable FPS and frame tokenization 27:35 What’s next for Gemini’s multimodal development 31:47 Deep dive on Gemini’s document understanding capabilities 37:56 The teamwork and collaboration behind Gemini 40:56 What’s next with model behavior

Google AI

58,703 views • 1 year ago

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!

This is, by far, one of the best uses of modern AI. If you don't use embeddings when querying your database, you are definitely leaving a lot on the table. In this video, I'll show you how to run semantic searches using OpenAI and PostgreSQL. It's all thanks to Pgai, an open-source PostgreSQL extension: Here's what will happen: 1. We'll create a simple table with news articles 2. We'll generate embeddings for those articles 3. We'll run queries on top of those embeddings For this video, I generated the embeddings using a simple query, but pgai Vectorizer would do the same automatically as new information makes it into the database. This is awesome! If you have a PostgreSQL database with data you are searching over, you should start experimenting with semantic searches immediately. For most use cases, a combination of full-text search + semantic search is the best approach. If you don't have a PostgreSQL database around, you can try free for 30 days using Timescale: Thanks to the TimescaleDB (by Tiger Data) team for partnering with me on this post!

Santiago

110,133 views • 1 year ago

Xiaomi delivered 550,000 vehicles in 20 months. And every single one uses Gigacasting. In 2020, Tesla pioneered Gigacasting. By 2024, Xiaomi was already in mass production - with self-developed alloys and now has 6 machines running at full capacity. But Xiaomi isn't alone. Here's what my database shows: → Xpeng launched 4 new Gigacast models in just 2 years → Seres (AITO) uses Gigacasting on ICE vehicles - not just EVs → Tesla still leads in process reduction, but Chinese OEMs are catching up fast I've built a side-by-side comparison of Tesla vs. three Chinese OEMs: Xpeng, Xiaomi, and Seres. It covers: - When each started Gigacasting and how they scaled - Machine sizes, suppliers, and production volumes - Design philosophy: why the castings are the way they are - Vertical integration vs. outsourcing tradeoffs This is the data behind the headlines. Want the Tesla vs China Gigacasting Comparison? 1. Connect with me 2. Comment "GIGA" below I'll send you the report. PS - Repost for priority access.

Xiaomi delivered 550,000 vehicles in 20 months. And every single one uses Gigacasting. In 2020, Tesla pioneered Gigacasting. By 2024, Xiaomi was already in mass production - with self-developed alloys and now has 6 machines running at full capacity. But Xiaomi isn't alone. Here's what my database shows: → Xpeng launched 4 new Gigacast models in just 2 years → Seres (AITO) uses Gigacasting on ICE vehicles - not just EVs → Tesla still leads in process reduction, but Chinese OEMs are catching up fast I've built a side-by-side comparison of Tesla vs. three Chinese OEMs: Xpeng, Xiaomi, and Seres. It covers: - When each started Gigacasting and how they scaled - Machine sizes, suppliers, and production volumes - Design philosophy: why the castings are the way they are - Vertical integration vs. outsourcing tradeoffs This is the data behind the headlines. Want the Tesla vs China Gigacasting Comparison? 1. Connect with me 2. Comment "GIGA" below I'll send you the report. PS - Repost for priority access.

Luca Greco

36,564 views • 7 months ago

Nick Fuentes talks about how he'd deal with Israel as President. 1- Put Military pressure on them 2- Strengthen their rivals to create balance 3- Eliminate the corruption in America 4- Assert control over them But they will never tolerate the existence of a Palestinian State.

Nick Fuentes talks about how he'd deal with Israel as President. 1- Put Military pressure on them 2- Strengthen their rivals to create balance 3- Eliminate the corruption in America 4- Assert control over them But they will never tolerate the existence of a Palestinian State.

KaizerRev

76,887 views • 2 months ago

Hunter Biden. 0:00 Why Did Hunter Sit Down With Candace Owens? 12:34 The Dark Side of Social Media 18:06 War, Insider Trading, and the Washington Elites 32:36 Thomas Massie and Marjorie Taylor Greene 35:21 The Importance of Self-Reflection 39:49 Addiction and Sobriety 48:31 The Unanswered Questions of the Hunter Biden Laptop Story 58:21 How Hunter Found Out About the Laptop Story 1:05:44 What Was Israel's Role in the Laptop Story? 1:12:12 Hunter Meeting His Wife and Overcoming Addiction 1:23:28 The Thing Far More Important Than Politics 1:31:51 The Dangers of AI 1:35:27 The Evils of Benjamin Netanyahu 1:36:57 How Alcohol Affects You and How to Get Sober 1:57:13 What Does Hunter's Wife Think About All This? 1:58:22 What's Hunter's Plan for the Future? 2:01:04 Hunter's Journey to Financial Freedom 2:04:34 Hunter's Relationship With God

Hunter Biden. 0:00 Why Did Hunter Sit Down With Candace Owens? 12:34 The Dark Side of Social Media 18:06 War, Insider Trading, and the Washington Elites 32:36 Thomas Massie and Marjorie Taylor Greene 35:21 The Importance of Self-Reflection 39:49 Addiction and Sobriety 48:31 The Unanswered Questions of the Hunter Biden Laptop Story 58:21 How Hunter Found Out About the Laptop Story 1:05:44 What Was Israel's Role in the Laptop Story? 1:12:12 Hunter Meeting His Wife and Overcoming Addiction 1:23:28 The Thing Far More Important Than Politics 1:31:51 The Dangers of AI 1:35:27 The Evils of Benjamin Netanyahu 1:36:57 How Alcohol Affects You and How to Get Sober 1:57:13 What Does Hunter's Wife Think About All This? 1:58:22 What's Hunter's Plan for the Future? 2:01:04 Hunter's Journey to Financial Freedom 2:04:34 Hunter's Relationship With God

Tucker Carlson

2,593,009 views • 1 month ago

PEOPLE OF THE EARTH. Figured out how to ask natural language questions of current financial data and get back a natural language response...with correct/relevant numbers! 🤯💰✨ So. Freaking. Cool. 1. Send database schema along with the question and relevant scope/parameters to GPT. 2. GPT returns SQL query. 3. Run SQL query on your data. 4. Take returned data and pass it in along with the original question. 5. GPT returns natural language answer with relevant data! Original Question: What was the highest price of Apple's stock over the past decade and how does it compare to Tesla's highest stock price? And on what date were those highest prices? Final Answer: The highest price of Apple's stock over the past decade was $182.94 on January 4, 2022, while Tesla's highest stock price was $414.50 on November 4, 2021.

PEOPLE OF THE EARTH. Figured out how to ask natural language questions of current financial data and get back a natural language response...with correct/relevant numbers! 🤯💰✨ So. Freaking. Cool. 1. Send database schema along with the question and relevant scope/parameters to GPT. 2. GPT returns SQL query. 3. Run SQL query on your data. 4. Take returned data and pass it in along with the original question. 5. GPT returns natural language answer with relevant data! Original Question: What was the highest price of Apple's stock over the past decade and how does it compare to Tesla's highest stock price? And on what date were those highest prices? Final Answer: The highest price of Apple's stock over the past decade was $182.94 on January 4, 2022, while Tesla's highest stock price was $414.50 on November 4, 2021.

Josh Pigford

245,304 views • 3 years ago

Most people think Rerun is a visualization tool. In reality, it's a database masquerading as a visualizer. I wanted to showcase this functionality by building a full data pipeline consisting of: ingestion → baseline method → eval → finetuning for SLAM on egocentric data. I'll eventually extend this to the rest of my ego/exo datasets, but I wanted to start with a smaller bunch of datasets first. Rerun allows you to expose your saved .rrd files to a catalog where you store datasets. You can query, filter, and join them like any database using DataFusion under the hood. These are the same .rrd files that are automatically generated whenever you visualize anything in Rerun and decide to save it to disk. I brought in 109 VSLAM-LAB sequences across 14 datasets into the Rerun catalog as an example. These include 7Scenes, Euroc, eth3d, and others. Now I can query them with segment_table, filter_segments, and filter_contents instead of parsing CSVs and YAML files. With a strong set of ground-truth datasets for SLAM, baseline additions become nearly automatic with agents like Opus/Codex. This unification of data and visualization is imo the largest missing part for Physical AI. Visualization becomes a natural byproduct of having your data properly structured and queryable. The catalog API is what makes it a database, not just a viewer. I initially focused on VSLAM-LAB data, but I'll migrate all the egoexo data to this format in the coming days to really show just how useful this is.

Most people think Rerun is a visualization tool. In reality, it's a database masquerading as a visualizer. I wanted to showcase this functionality by building a full data pipeline consisting of: ingestion → baseline method → eval → finetuning for SLAM on egocentric data. I'll eventually extend this to the rest of my ego/exo datasets, but I wanted to start with a smaller bunch of datasets first. Rerun allows you to expose your saved .rrd files to a catalog where you store datasets. You can query, filter, and join them like any database using DataFusion under the hood. These are the same .rrd files that are automatically generated whenever you visualize anything in Rerun and decide to save it to disk. I brought in 109 VSLAM-LAB sequences across 14 datasets into the Rerun catalog as an example. These include 7Scenes, Euroc, eth3d, and others. Now I can query them with segment_table, filter_segments, and filter_contents instead of parsing CSVs and YAML files. With a strong set of ground-truth datasets for SLAM, baseline additions become nearly automatic with agents like Opus/Codex. This unification of data and visualization is imo the largest missing part for Physical AI. Visualization becomes a natural byproduct of having your data properly structured and queryable. The catalog API is what makes it a database, not just a viewer. I initially focused on VSLAM-LAB data, but I'll migrate all the egoexo data to this format in the coming days to really show just how useful this is.

Pablo Vela

35,179 views • 4 months ago

I just listened to the new podcast with the $NET dev, Al Dunlap, by BlockRunners - and I became even more bullish. Al explains how this world is currently being hyper-gamblified, and Gen Z rather gambles than buying stocks. (data shows this to be true) Through NetNet, he wants to gamify the way people get introduced to equities, by making games where instead of receiving cash these player win Nvidia or Tesla stock. Which falls very in-line with Robinhood/Vlad’s thesis of why they build the Robinhood chain. He also understands that he can’t do this alone, so he’s building the infrastructure where this meta called RW-Play can evolve on (all with the goal of growing the $NET treasury), and already working on bringing in proven teams. At the end he mentioned he’s working closely with Robinhood to build this idea out, and that he has 2 teams with big distribution channels integrating their games on NetNet’s Turbo product. Al Dunlap is single-handedly kickstarting the new big meta of this cycle. (just like he did with NBA Topshot) The near future looks very bright for NetNet Capital. (🥅,🥅)

I just listened to the new podcast with the $NET dev, Al Dunlap, by BlockRunners - and I became even more bullish. Al explains how this world is currently being hyper-gamblified, and Gen Z rather gambles than buying stocks. (data shows this to be true) Through NetNet, he wants to gamify the way people get introduced to equities, by making games where instead of receiving cash these player win Nvidia or Tesla stock. Which falls very in-line with Robinhood/Vlad’s thesis of why they build the Robinhood chain. He also understands that he can’t do this alone, so he’s building the infrastructure where this meta called RW-Play can evolve on (all with the goal of growing the $NET treasury), and already working on bringing in proven teams. At the end he mentioned he’s working closely with Robinhood to build this idea out, and that he has 2 teams with big distribution channels integrating their games on NetNet’s Turbo product. Al Dunlap is single-handedly kickstarting the new big meta of this cycle. (just like he did with NBA Topshot) The near future looks very bright for NetNet Capital. (🥅,🥅)

chjokka

23,273 views • 1 month ago