Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

💥 OSS product analytics for LLM apps. Launching PostHog x langfuse.com integration 🤝 🫳 Day 1 drop of Langfuse Launch Week: We’re marrying product analytics and LLM observability. This integration pipes Langfuse events/metrics/evals into your PostHog project. This allows you to access all of your LLM metrics straight from...

marcklingen's profile picture

Marc Klingen

3,341 subscribers

15,658 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

10 Kommentare

Profilbild von Marc Klingen
Marc Klingenvor 2 Jahren

@langfuse Looking forward to @hassiebpakzad's drop on Day 2 ✨

Profilbild von Clemens Rawert
Clemens Rawertvor 2 Jahren

@posthog @langfuse just getting started!

Profilbild von Thomas Paul Mann
Thomas Paul Mannvor 2 Jahren

@posthog @langfuse Very cool!

Profilbild von Hassieb Pakzad
Hassieb Pakzadvor 2 Jahren

@posthog @langfuse 🚀🚀🚢🚢

Profilbild von Marc Klingen
Marc Klingenvor 2 Jahren

@posthog @langfuse might just rename it to `ship week` or `ltgm week`

Profilbild von Brandon
Brandonvor 2 Jahren

@posthog @langfuse Dope! I just started using posthog this weekend.

Profilbild von Marc Klingen
Marc Klingenvor 2 Jahren

@posthog @langfuse great choice, posthog is awesome and super versatile with its many SDKs. we've been using it to track front-end events, backend ingestion metrics, and very basic self-hosting telemetry let me know if you have any feedback while getting started with this integration

Profilbild von Lior Neu-ner
Lior Neu-nervor 2 Jahren

@posthog @langfuse 🔥🔥🔥

Profilbild von Alex Krausse
Alex Kraussevor 2 Jahren

@rawert @posthog @langfuse 🚀🙌

Profilbild von Nikhil Kulkarni
Nikhil Kulkarnivor 2 Jahren

@posthog @langfuse 🔥🔥

Ähnliche Videos

PostHog Changelog, S1E1: Warm Green Space Goo - Experiments: You can now measure declines in metrics, like account deactivations, during experiments. Why? Because sometimes "up and to the right" isn't the correct goal. - Max AI: Max can now generate surveys in seconds using natural language. Just go to the Surveys product and start telling Max what your dream survey looks like. - Max AI: You can now add existing insights, dashboards, events, and actions as context to your conversations with Max. Try using this to summarize the trends on a dashboard, or analyze how a key metric is trending over time.
1:38

PostHog Changelog, S1E1: Warm Green Space Goo - Experiments: You can now measure declines in metrics, like account deactivations, during experiments. Why? Because sometimes "up and to the right" isn't the correct goal. - Max AI: Max can now generate surveys in seconds using natural language. Just go to the Surveys product and start telling Max what your dream survey looks like. - Max AI: You can now add existing insights, dashboards, events, and actions as context to your conversations with Max. Try using this to summarize the trends on a dashboard, or analyze how a key metric is trending over time.

PostHog

17,131 Aufrufe • vor 10 Monaten

Introducing PostHog 3000 & Notebooks 🎉 As an end of year gift to our awesome users, we've released a major overhaul of the PostHog user experience. Our goal with this redesign is to make PostHog feel less like a SaaS app and more like a dev tool. ✅ It's got dark mode! ✅ It's got data density! ✅ It's got side panels! ✅ It's got... notebooks? Notebooks is a new, free feature that's integral to the PostHog 3000 experience. Think of them as an ever-present place to collect data, explore it, add context, and share with others. Investigating a bug report? 🐞 Drag and drop session replays into a notebook. Researching a new idea? 💡 Collect insights and add them to your proposal seamlessly, alongside survey results or cohorts. Planning a launch? 🚀 Embed the feature flags, events, persons, or cohorts you'll need to deploy changes and track success. Notebooks make analyzing data and sharing your findings effortless – see the video demo for more. We have way more planned for Notebooks and PostHog 3000 in 2024, such as: 🔔 A new activity feed 📔 Notebook templates ⌨️ Way more keyboard shortcuts 💬 Comments, replies and mentions (coming very soon) We hope you enjoy the update and, as ever, please share your feedback (it's even easier to do in PostHog 3000!). Thank you for your support. 🙌
2:36

Introducing PostHog 3000 & Notebooks 🎉 As an end of year gift to our awesome users, we've released a major overhaul of the PostHog user experience. Our goal with this redesign is to make PostHog feel less like a SaaS app and more like a dev tool. ✅ It's got dark mode! ✅ It's got data density! ✅ It's got side panels! ✅ It's got... notebooks? Notebooks is a new, free feature that's integral to the PostHog 3000 experience. Think of them as an ever-present place to collect data, explore it, add context, and share with others. Investigating a bug report? 🐞 Drag and drop session replays into a notebook. Researching a new idea? 💡 Collect insights and add them to your proposal seamlessly, alongside survey results or cohorts. Planning a launch? 🚀 Embed the feature flags, events, persons, or cohorts you'll need to deploy changes and track success. Notebooks make analyzing data and sharing your findings effortless – see the video demo for more. We have way more planned for Notebooks and PostHog 3000 in 2024, such as: 🔔 A new activity feed 📔 Notebook templates ⌨️ Way more keyboard shortcuts 💬 Comments, replies and mentions (coming very soon) We hope you enjoy the update and, as ever, please share your feedback (it's even easier to do in PostHog 3000!). Thank you for your support. 🙌

PostHog

26,263 Aufrufe • vor 2 Jahren

🚨 There are more cool things in PostHog: - Max AI has evolved into PostHog AI. It can now navigate the app, create feature flags, and is automatically aware of the active tab. - PostHog AI's updated chat UI now shows its reasoning, planning, and tool calling all in real-time. - You can now schedule changes to *existing* feature flags, making it even easier to manage release conditions. - Export up to 15 second session replay clips to MP4 or GIFs. Memes not guaranteed. - Our new beta SDK Doctor will alert you when you're running an out-of-date SDK - Android and Flutter SDKs now support error tracking (beta) - Long session replays now take less time to buffer by only loading 15 mins at a time - New tab UI that shows you most recently visited pages at the top - You can now pin tabs, so you can now have pinned tabs inside your pinned tabs. We call this Tabception - Sort error tracking issues by revenue impact (if you've setup revenue analytics, so you should probably do that!) - TikTok Ads as a data source
3:54

🚨 There are more cool things in PostHog: - Max AI has evolved into PostHog AI. It can now navigate the app, create feature flags, and is automatically aware of the active tab. - PostHog AI's updated chat UI now shows its reasoning, planning, and tool calling all in real-time. - You can now schedule changes to *existing* feature flags, making it even easier to manage release conditions. - Export up to 15 second session replay clips to MP4 or GIFs. Memes not guaranteed. - Our new beta SDK Doctor will alert you when you're running an out-of-date SDK - Android and Flutter SDKs now support error tracking (beta) - Long session replays now take less time to buffer by only loading 15 mins at a time - New tab UI that shows you most recently visited pages at the top - You can now pin tabs, so you can now have pinned tabs inside your pinned tabs. We call this Tabception - Sort error tracking issues by revenue impact (if you've setup revenue analytics, so you should probably do that!) - TikTok Ads as a data source

PostHog

12,050 Aufrufe • vor 8 Monaten

Our revolutionary $0 multichain AI launcher via Telegram is coming!🔥 Integration with Base and BSC is complete, and SOL integration is on track to be finalised by the end of the week 🚀 At present, private parties are testing it on the testnet to refine its performance while we prepare it for auditing.🤝 This groundbreaking and innovative product is truly one of a kind, seamlessly integrating with your favourite social media platforms. ✅ Picture this: your favourite alpha community on telegram, one of thousands transparently launching a token where the entire community can share in its success and network effects. All of this happens without ever needing to leave the app, unlike the most popular platforms currently available. 📈
0:24

Our revolutionary $0 multichain AI launcher via Telegram is coming!🔥 Integration with Base and BSC is complete, and SOL integration is on track to be finalised by the end of the week 🚀 At present, private parties are testing it on the testnet to refine its performance while we prepare it for auditing.🤝 This groundbreaking and innovative product is truly one of a kind, seamlessly integrating with your favourite social media platforms. ✅ Picture this: your favourite alpha community on telegram, one of thousands transparently launching a token where the entire community can share in its success and network effects. All of this happens without ever needing to leave the app, unlike the most popular platforms currently available. 📈

SocialGrowAI

57,657 Aufrufe • vor 1 Jahr

#HUMAINChat is LIVE! Today marks a moment of pride - not only for but for all of Saudi Arabia with the launch of HUMAIN Chat, powered by ALLAM34B, the most advanced Arabic-first LLM built in the Arab world fluent in our culture, our values, and our heritage. It was deeply important to me to deliver this message to you, the Saudi people, in your native language. I recognize that my Arabic isn’t perfect, but just like me, HUMAIN Chat is still improving. And this is where I need your support. Your conversations and interactions with HUMAIN Chat will directly help improve the LLM powering it. This is your opportunity to shape a Saudi-born, Arabic-first digital product into the best of its kind before we roll it out to the world. Download HUMAIN Chat now and make it your go-to AI companion: #HUMAINAI #TheEndOfLimits
0:57

#HUMAINChat is LIVE! Today marks a moment of pride - not only for but for all of Saudi Arabia with the launch of HUMAIN Chat, powered by ALLAM34B, the most advanced Arabic-first LLM built in the Arab world fluent in our culture, our values, and our heritage. It was deeply important to me to deliver this message to you, the Saudi people, in your native language. I recognize that my Arabic isn’t perfect, but just like me, HUMAIN Chat is still improving. And this is where I need your support. Your conversations and interactions with HUMAIN Chat will directly help improve the LLM powering it. This is your opportunity to shape a Saudi-born, Arabic-first digital product into the best of its kind before we roll it out to the world. Download HUMAIN Chat now and make it your go-to AI companion: #HUMAINAI #TheEndOfLimits

Tareq Amin

52,845 Aufrufe • vor 11 Monaten

📣 Drop everything now... because Lumio's integration with Canva Education is now LIVE! 🙌🏻 You'll be able to save teacher time this #BacktoSchool year by creating cool content in Canva and then easily exporting it into Lumio to add the magic of Lumio’s interactivity and game-based learning to your lessons. Learn more about this game-changing integration here: We can't wait to see all of your creative lesson content! 💛 #TeacherTwitter #GoLumio
0:25

📣 Drop everything now... because Lumio's integration with Canva Education is now LIVE! 🙌🏻 You'll be able to save teacher time this #BacktoSchool year by creating cool content in Canva and then easily exporting it into Lumio to add the magic of Lumio’s interactivity and game-based learning to your lessons. Learn more about this game-changing integration here: We can't wait to see all of your creative lesson content! 💛 #TeacherTwitter #GoLumio

Lumio 💛

12,283 Aufrufe • vor 3 Jahren

i wish i could just upload a CSV and it would automatically create a dashboard so we built this today we're launching graphed .com graphed is an AI data analytics and dashboard generator upload data into Graphed and it's gonna one shot generate a dashboard you can chat with the entire dashboard to make changes and you can click into the graph and chat with it to make updates everything you create in Graphed can easily be shared with your team by sending a link or you can download a screenshot and drop it into a Slack channel or add it to a presentation the Graphed source data can either be a CSV or a data integration data integrations allow you to create live dashboards that are constantly updating in the background we're launching with Google Analytics 4 as our first data integration but we have Shopify, Facebook ads, Google Ads, MongoDB, and hundreds more are on our product roadmap you can sign up for free at graphed .com and if you want a 40% discount code that will only be available during launch comment "graphed" below
0:52

i wish i could just upload a CSV and it would automatically create a dashboard so we built this today we're launching graphed .com graphed is an AI data analytics and dashboard generator upload data into Graphed and it's gonna one shot generate a dashboard you can chat with the entire dashboard to make changes and you can click into the graph and chat with it to make updates everything you create in Graphed can easily be shared with your team by sending a link or you can download a screenshot and drop it into a Slack channel or add it to a presentation the Graphed source data can either be a CSV or a data integration data integrations allow you to create live dashboards that are constantly updating in the background we're launching with Google Analytics 4 as our first data integration but we have Shopify, Facebook ads, Google Ads, MongoDB, and hundreds more are on our product roadmap you can sign up for free at graphed .com and if you want a 40% discount code that will only be available during launch comment "graphed" below

Cody Schneider

47,255 Aufrufe • vor 1 Jahr

AI is insecure by default. The open secret is that most AI apps launch with serious flaws. It takes MORE time to secure these apps than it does to build them. I learned this firsthand from shipping LLM agents to 200M users at Discord and supporting LLM evals for hundreds of companies. It doesn’t have to be this way. Today, we’re launching promptfoo, an open-source company that helps find and fix vulnerabilities in AI powered apps before they ship, and announcing a $5M seed round led by a16z.
1:01

AI is insecure by default. The open secret is that most AI apps launch with serious flaws. It takes MORE time to secure these apps than it does to build them. I learned this firsthand from shipping LLM agents to 200M users at Discord and supporting LLM evals for hundreds of companies. It doesn’t have to be this way. Today, we’re launching promptfoo, an open-source company that helps find and fix vulnerabilities in AI powered apps before they ship, and announcing a $5M seed round led by a16z.

Ian Webster

28,779 Aufrufe • vor 2 Jahren

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:
2:07

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

Andrew Ng

126,406 Aufrufe • vor 1 Jahr

This is literally the simplest way you can improve your LLM-based application. It takes 2 lines of code to integrate Lilypad, and you'll get full observability into everything your app is doing: • Automatic traces • Costs • Tokens consumed • Metadata On top of that, you can annotate your traces to evaluate different versions of your prompts. Here is Lilypad's GitHub Repository: This is a no-brainer. Check out the video and you'll see how cool this is.
5:14

This is literally the simplest way you can improve your LLM-based application. It takes 2 lines of code to integrate Lilypad, and you'll get full observability into everything your app is doing: • Automatic traces • Costs • Tokens consumed • Metadata On top of that, you can annotate your traces to evaluate different versions of your prompts. Here is Lilypad's GitHub Repository: This is a no-brainer. Check out the video and you'll see how cool this is.

Santiago

42,170 Aufrufe • vor 1 Jahr

99% of session replays are your app working exactly as expected (hopefully) The other 1% is where the friction hides The bugs. The failed onboarding flows. The conversion leaks. No team has time to watch them all... That's the problem Michael and his co-founder kept hitting at their last company They had analytics. They had session replays. They had ideas to improve conversion. The small fixes always lost to bigger priorities... So they pivoted and built CodeCanary: An AI product engineer that connects to GitHub, PostHog, and Slack It watches your session replays, finds the UX friction, and opens pull requests with the fix Always on. Always shipping. Not dashboards Not alerts Actual fixes 🎙️ Michael Egan, CEO & Co-Founder, CodeCanary on Fondo.com START (full ep in comments) Big thanks to PostHog for making this episode possible!
0:59

99% of session replays are your app working exactly as expected (hopefully) The other 1% is where the friction hides The bugs. The failed onboarding flows. The conversion leaks. No team has time to watch them all... That's the problem Michael and his co-founder kept hitting at their last company They had analytics. They had session replays. They had ideas to improve conversion. The small fixes always lost to bigger priorities... So they pivoted and built CodeCanary: An AI product engineer that connects to GitHub, PostHog, and Slack It watches your session replays, finds the UX friction, and opens pull requests with the fix Always on. Always shipping. Not dashboards Not alerts Actual fixes 🎙️ Michael Egan, CEO & Co-Founder, CodeCanary on Fondo.com START (full ep in comments) Big thanks to PostHog for making this episode possible!

David J Phillips

21,677 Aufrufe • vor 1 Monat

The New $KOL Telegram Bot feature is here - Introducing The Project Checker. Now, you can not only check KOLs but also check ANY PROJECT you want. Earn points by checking, sharing and posting projects cards on X. This should give you a glimpse into the actual Closed Beta coming in 2 weeks. 👀 Project Checker will give you the following metrics: - Followers & Smart Followers Counts - Top 3 Contributors (number of posts, views, interactions) - Total X contributors - Project views - Organic views (views generated by contributors) - Token performance in the past 30 days Check projects, share their cards to your friends or post them on Twitter. (TG Bot link in comments) 👇
0:27

The New $KOL Telegram Bot feature is here - Introducing The Project Checker. Now, you can not only check KOLs but also check ANY PROJECT you want. Earn points by checking, sharing and posting projects cards on X. This should give you a glimpse into the actual Closed Beta coming in 2 weeks. 👀 Project Checker will give you the following metrics: - Followers & Smart Followers Counts - Top 3 Contributors (number of posts, views, interactions) - Total X contributors - Project views - Organic views (views generated by contributors) - Token performance in the past 30 days Check projects, share their cards to your friends or post them on Twitter. (TG Bot link in comments) 👇

ProtoKOLs

69,516 Aufrufe • vor 1 Jahr

The Studio Beta is Live ⚡️ After weeks of onboarding calls & preparations - all Beta Testers now have exclusive access to the Beta Studio For the next 2 weeks, we challenged them to train & fine-tune as many AI models as they can with their own data This phase is a crucial part of our iterative process towards the V1, and by involving real users from the start we ensure the final product is intuitive and packed with the functionalities you need We're not just building this for you - we're building this with you.
0:38

The Studio Beta is Live ⚡️ After weeks of onboarding calls & preparations - all Beta Testers now have exclusive access to the Beta Studio For the next 2 weeks, we challenged them to train & fine-tune as many AI models as they can with their own data This phase is a crucial part of our iterative process towards the V1, and by involving real users from the start we ensure the final product is intuitive and packed with the functionalities you need We're not just building this for you - we're building this with you.

Vertical AI

90,886 Aufrufe • vor 1 Jahr

Big news: shopdev is live, your AI developer for Shopify. The first 1,000 people who comment “shopdev” get access today and receive 250K tokens. Connect your Shopify store. And prompt custom sections using your actual products, collections, and theme styles. We've been deeply focused on the LLM space, working to unlock the full potential of AI for Shopify. Today, we finally did it. With shopdev, you can generate clean Liquid code that’s ready to ship — or publish straight to your theme in one click. This is day 1 of shopdev, and we hope to roll this out to everyone as soon as possible! See shopdev in action🧵
0:36

Big news: shopdev is live, your AI developer for Shopify. The first 1,000 people who comment “shopdev” get access today and receive 250K tokens. Connect your Shopify store. And prompt custom sections using your actual products, collections, and theme styles. We've been deeply focused on the LLM space, working to unlock the full potential of AI for Shopify. Today, we finally did it. With shopdev, you can generate clean Liquid code that’s ready to ship — or publish straight to your theme in one click. This is day 1 of shopdev, and we hope to roll this out to everyone as soon as possible! See shopdev in action🧵

Coen van Hees

219,417 Aufrufe • vor 1 Jahr

We worked with OpenAI to build a native integration for the OpenAI Agents SDK. Today, we are very excited to launch as a tracing processor. With just a few lines of code, you can trace all your agent workflows and debug them much faster. Check out this quick demo to get started:
0:49

We worked with OpenAI to build a native integration for the OpenAI Agents SDK. Today, we are very excited to launch as a tracing processor. With just a few lines of code, you can trace all your agent workflows and debug them much faster. Check out this quick demo to get started:

Respan

58,055 Aufrufe • vor 1 Jahr

We’re excited to announce that our integration with Patreon is live! Now you can add Patreon as a destination in either Streamlabs Desktop or the Plugin for OBS, and take advantage of your favorite Streamlabs features like multistream, dual output, and more!
0:33

We’re excited to announce that our integration with Patreon is live! Now you can add Patreon as a destination in either Streamlabs Desktop or the Plugin for OBS, and take advantage of your favorite Streamlabs features like multistream, dual output, and more!

Streamlabs

54,583 Aufrufe • vor 2 Monaten

NotebookLM is one of the most delightful, inspiring, and viral AI products out there right now, and I got a chance to chat with the PM behind the product, Raiza Martin (@raiza_abubakar). In our conversation, we cover: 🔸 The origin story of NotebookLM 🔸 The future road map for NotebookLM 🔸 How Google Labs operates differently from the rest of Google 🔸 The development of the “Audio Overviews” feature 🔸 Key metrics and growth of NotebookLM 🔸 Stories about collaborating with author Steven Johnson 🔸 Navigating potential misuse of AI technology 🔸 More Listen now 👇 - YouTube: - Spotify: - Apple: Raiza is a senior product manager for AI at Google Labs for AI at Google Labs, where she leads the team behind NotebookLM, an AI-powered research tool that includes a mind-blowing podcast-on-demand feature called “Audio Overviews.” NotebookLM started as a 20% project and has grown into a product that’s spreading across social media and has a Discord server with over 60,000 users. Raiza previously worked on AI Test Kitchen and has a background in startups, payments, and ads. Thank you to our wonderful sponsors for supporting the podcast: 🏆 Explo — Embed customer-facing analytics in your product: 🏆 Sprig — Build products for people, not data points: 🏆 Sidebar — Accelerate your career by surrounding yourself with extraordinary peers: Some key takeaways: 1. Embrace a startup mentality within large organizations: Google Labs operates with fewer processes and more agility than typical Google teams. This allows them to move faster and iterate quickly, much like a startup. 2. Often, powerful technology is already available; the magic lies in how you interact with it. For instance, by integrating powerful audio models with existing LLMs, NotebookLM created an innovative way for users to interact with content. Look for unique applications of the tools you already have. 3. Don’t wait for a perfect launch. Start with a working version of your product and use user feedback to iterate and improve. This approach can reveal unexpected insights and user preferences, helping you shape the final product.
1:07

NotebookLM is one of the most delightful, inspiring, and viral AI products out there right now, and I got a chance to chat with the PM behind the product, Raiza Martin (@raiza_abubakar). In our conversation, we cover: 🔸 The origin story of NotebookLM 🔸 The future road map for NotebookLM 🔸 How Google Labs operates differently from the rest of Google 🔸 The development of the “Audio Overviews” feature 🔸 Key metrics and growth of NotebookLM 🔸 Stories about collaborating with author Steven Johnson 🔸 Navigating potential misuse of AI technology 🔸 More Listen now 👇 - YouTube: - Spotify: - Apple: Raiza is a senior product manager for AI at Google Labs for AI at Google Labs, where she leads the team behind NotebookLM, an AI-powered research tool that includes a mind-blowing podcast-on-demand feature called “Audio Overviews.” NotebookLM started as a 20% project and has grown into a product that’s spreading across social media and has a Discord server with over 60,000 users. Raiza previously worked on AI Test Kitchen and has a background in startups, payments, and ads. Thank you to our wonderful sponsors for supporting the podcast: 🏆 Explo — Embed customer-facing analytics in your product: 🏆 Sprig — Build products for people, not data points: 🏆 Sidebar — Accelerate your career by surrounding yourself with extraordinary peers: Some key takeaways: 1. Embrace a startup mentality within large organizations: Google Labs operates with fewer processes and more agility than typical Google teams. This allows them to move faster and iterate quickly, much like a startup. 2. Often, powerful technology is already available; the magic lies in how you interact with it. For instance, by integrating powerful audio models with existing LLMs, NotebookLM created an innovative way for users to interact with content. Look for unique applications of the tools you already have. 3. Don’t wait for a perfect launch. Start with a working version of your product and use user feedback to iterate and improve. This approach can reveal unexpected insights and user preferences, helping you shape the final product.

Lenny Rachitsky

75,439 Aufrufe • vor 1 Jahr

Thank you guys for watching and supporting KNOW YOUR IN-BIRTH, EPISODE 4 - Carmine. I'm very happy to see the project growing episode by episode and all of this its because of you, viewer! You can check the full episode in this link: + If you enjoy my project and would like to help keep it going, consider making a donation. Any amount makes a difference! 💖 Thank you for your support and kindness!
0:29

Thank you guys for watching and supporting KNOW YOUR IN-BIRTH, EPISODE 4 - Carmine. I'm very happy to see the project growing episode by episode and all of this its because of you, viewer! You can check the full episode in this link: + If you enjoy my project and would like to help keep it going, consider making a donation. Any amount makes a difference! 💖 Thank you for your support and kindness!

Jinta (ジンタ) @UNI2

14,338 Aufrufe • vor 1 Jahr