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.

Week 3 of YC. We just made semantic search serverless. Until now, semantic search meant embedding every document, every row and every chunk up front, and paying for it before anyone ran a single search. We flipped that. With Polygres (YC F26) you connect your data, choose what's searchable,... show more

dale

4,066 subscribers

21,992 views • 11 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

45 Comments

dale11 days ago

Sign up for a free account:

Tejas11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Wtf crazzyy!!

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Hehehe

Shahab Uddin Ahmed Ohi11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Week 3 and you flipped the embedding bill. Intern searches refund and that is the whole demo.

Shivank Kapur11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc check dms @daleverett

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc What’s up?

Shivank Kapur11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc sent something 🫡

Deep Insight Labs11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Interesting...have a technical write-up somewhere?

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Full launch coming in the next few days.

Deep Insight Labs11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Looking forward to it!

adriel11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Fireee

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc 🔥 🔥

Hasnain Baig11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Actually insane

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc I’m as suprised as you are

Sidhdharth (Sid)11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Let's goooo legend

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Lfggg

Atharva Verma11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc how do you handle deltas and do you think it can be used in, for example, notion's semantic search?

Bryant11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc hella good work, Dale. Keep going.

ParvKasliwal11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc I have something really interesting to share regarding Polygres

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Dm me!

ParvKasliwal11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Dm'ed you

David T Kramaley10 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Turning semantic search into a pay‑per‑query model cuts the upfront barrier. Nice work

Chinsanity11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc nice seeing a founder from asia!

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Hehehe I’m from Singapore!

Punyakrit11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc i want to use it

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Dm me your polygres email

Punyakrit11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc sent

Daniel10 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc pgGraph 🤯 intriguing, huge utility to a certain size i'd wager then, lose dual benefit of building proper KG for ML of underserved relationships >

MrOzi11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Serverless semantic search: finally, the database bills you only when someone actually asks a question.

Peter Orban10 days ago

Hi Dale! I think flipping semantic search so you pay for tokens only when someone actually searches is the part that changes the economics for sparse corpora. In my opinion, matching embedding-model recall without a neural ingestion pass is the claim that will get stress tested first on messy tables. Where does recall drop first in your internal benchmarks, short fields or long documents?

BeeReach11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc looks solid, serverless semantic search could cut costs a lot. how does latency compare on bigger datasets?

0xJiuJitsuJerry11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc This is awesome, Dale. I’ve already seen Polygres retrieve my past posts, project notes, and visual concepts by meaning. Then help my AI agent connect them into something new. Making that experience serverless, and usage based lowers a huge barrier for builders like me. 🧠

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Thank you! Will give you access asap

Daeshawn | Nargis10 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Bullish

everett11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc get it brooo

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Heheh

Avinash Dalvi10 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc without embedding anything up front, what does the model actually read when a search comes? If it goes through every row each time, does latency and token cost grow with table size, or is there some cheap index narrowing it down first?

bryan10 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc would love to benchmark this on real world tasks in comparison to our hyrid rag solution! if you arent embedding it upfront based on what are you searching then?

dale10 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc coming out in about 30 mins :) keep your eyes peeled for our launch video!

Bernadette10 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Dale lemme try this!!

dale10 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc I will! Dm me what ur thinking of using it for!

jawad.jalal11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc good stuff

dale11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc Hehe

Zero10 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc

John Rood11 days ago

@polygres @daltonmeon @damienhe @ycombinator @fdotinc the flip is real, with one inversion: embeddings paid once amortize across every future query, while query-time pays full price on the thousandth search too. right for cold corpora, wrong for the docs your agents hit all day. those queries should materialize, not recompute.

Related Videos

Filesystems vs Vector search is the new MCP vs CLI. Claude uses agentic search. And Dens Sumesh at mintlify like filesystems too. but Retrieval is still used by Notion, Cursor, and others. We hit the cafes of SF to see what people want. - The debate is hot. Filesystems won by 1 point - filesystems feel very simple and intuitive. - RAG requires embedding, vector search and other stuff filesystems won. Introducing SMFS - Supermemory Filesystem we brought the best of these worlds into one single product - it's a filesystem, but agent can also do semantic search using grep. live today. Try it! Works with any sandbox, you mount and sync with cloud, it has a sync engine built in, all filetypes supported - even images and videos can be grepped. So, what do you choose - Filesystems, or vector search? we have both!

Filesystems vs Vector search is the new MCP vs CLI. Claude uses agentic search. And Dens Sumesh at mintlify like filesystems too. but Retrieval is still used by Notion, Cursor, and others. We hit the cafes of SF to see what people want. - The debate is hot. Filesystems won by 1 point - filesystems feel very simple and intuitive. - RAG requires embedding, vector search and other stuff filesystems won. Introducing SMFS - Supermemory Filesystem we brought the best of these worlds into one single product - it's a filesystem, but agent can also do semantic search using grep. live today. Try it! Works with any sandbox, you mount and sync with cloud, it has a sync engine built in, all filetypes supported - even images and videos can be grepped. So, what do you choose - Filesystems, or vector search? we have both!

Dhravya Shah

153,119 views • 5 months ago

We’re expanding the Gemini API File Search tool 🔍 with 3 new updates that enable developers to more easily build multimodal RAG systems with enhanced precision: + Multimodal Support: By leveraging our Gemini Embedding 2 model, File Search can now reason across image and text simultaneously. + Custom Metadata Filtering: Bring structure to unstructured data by tagging files with custom key-value labels. This pre-filters your data and boosts search speed. + Exact citations: File Search can now capture and return the exact source (down to the page number) for every piece of information indexed. See multimodal File Search in action with our example app in Google AI Studio. Chat with your entire image and doc library, ask questions, and trace answers back to the source:

We’re expanding the Gemini API File Search tool 🔍 with 3 new updates that enable developers to more easily build multimodal RAG systems with enhanced precision: + Multimodal Support: By leveraging our Gemini Embedding 2 model, File Search can now reason across image and text simultaneously. + Custom Metadata Filtering: Bring structure to unstructured data by tagging files with custom key-value labels. This pre-filters your data and boosts search speed. + Exact citations: File Search can now capture and return the exact source (down to the page number) for every piece of information indexed. See multimodal File Search in action with our example app in Google AI Studio. Chat with your entire image and doc library, ask questions, and trace answers back to the source:

Google AI Developers

108,801 views • 5 months ago

I don’t think people realize the scale of data behind the JBP Search Engine. Every single episode since Episode 1 has been transcribed and converted into embeddings for semantic search. This isn’t keyword matching. It understands the context of your query and returns the exact moment you’re looking for…not just a list of episodes where something was mentioned. 1,415 episodes. ~3 hours each. Over 600GB of locally stored audio + additional metadata powering search quality. Could you do it? Maybe, but just know, I’ve personally spent thousands of dollars in compute to make this possible. There’s no way around it when dealing with this much data.

I don’t think people realize the scale of data behind the JBP Search Engine. Every single episode since Episode 1 has been transcribed and converted into embeddings for semantic search. This isn’t keyword matching. It understands the context of your query and returns the exact moment you’re looking for…not just a list of episodes where something was mentioned. 1,415 episodes. ~3 hours each. Over 600GB of locally stored audio + additional metadata powering search quality. Could you do it? Maybe, but just know, I’ve personally spent thousands of dollars in compute to make this possible. There’s no way around it when dealing with this much data.

burner account

130,997 views • 4 months ago

Our Ultra and Pro subs have been using info monitoring capabilities in AI Mode in Search, and now we’re rolling it out to everyone globally. Just tell AI Mode exactly what to look for & Search will continuously check across changing info on the web like sites, forums and social posts, our real-time data sources, and Shopping Graph of 60B+ products, so you can stay up-to-date with fresh info. And it’ll even suggest tasks when you’re searching so you can get the latest info when it happens. It puts Search to work right as you explore, especially for topics you keep coming back to: > New restaurants or pop-ups open near me > Local holiday stuff to do with the kids > Back in stock & price drop updates Now rolling out to all users in Search globally – check it out today in the Google app. Lots more to come!

Our Ultra and Pro subs have been using info monitoring capabilities in AI Mode in Search, and now we’re rolling it out to everyone globally. Just tell AI Mode exactly what to look for & Search will continuously check across changing info on the web like sites, forums and social posts, our real-time data sources, and Shopping Graph of 60B+ products, so you can stay up-to-date with fresh info. And it’ll even suggest tasks when you’re searching so you can get the latest info when it happens. It puts Search to work right as you explore, especially for topics you keep coming back to: > New restaurants or pop-ups open near me > Local holiday stuff to do with the kids > Back in stock & price drop updates Now rolling out to all users in Search globally – check it out today in the Google app. Lots more to come!

Robby Stein

22,921 views • 10 days ago

After several years of declining search traffic, Condé Nast CEO Roger Lynch has directed all the company's brands to operate as if search traffic to their properties will be zero. He says the era of turning search and social media traffic into profitable businesses is gone. And that if you run a media business that doesn't have an authoritative brand, a very strong niche, or a direct audience, you're going to be fighting hostile algo changes all the way down. He describes a recent board meeting: "We took a snapshot of search results from seven or eight years ago. And what you saw were a few sponsored links, then the ten blue links." "Do the same search today, you get an AI overview, then you get rows and rows and rows of commerce links, then you get sponsored stuff." "Each of the last three years, we would do our budgets, and we'd put forecasts in of search traffic declining. Because we'd seen the pattern of algorithm changes. And generally those algorithm changes were negative." "Every year, our search traffic was down more than we had forecast. So last year I told our teams, 'Assume there's no search.' You have to have your businesses planned as if search is zero. We don't expect it to be zero, we expect it to be a single-digit percentage of our traffic."

TBPN

330,003 views • 4 months ago

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

Robby Stein

94,962 views • 10 months ago

I just built an AI-powered creative search engine with Gemini Embedding 2 + Claude Code 🤯 Drop in your UGC clips, product shots, and ad variations — then search through everything in plain English. "Show me all the unboxing clips." "Find product shots with natural lighting." "Which creator talked about sensitive skin?" All inside Claude Code. Perfect for DTC brands and agencies sitting on hundreds of creative files they can never find when they actually need them. If you're digging through a folder of random file names, scrubbing through raw footage to find that one clip, and relying on memory to track down what's already been shot... This system eliminates the entire loop: → Drop your videos, images, and docs into a project folder → One prompt to Claude Code — it builds the entire search app for you → Google's new Gemini Embedding 2 model actually watches your videos and looks at your images → It understands what's inside each file — not just the file name → Search in plain English and get back the actual assets with confidence scores No scrolling through folders. No relying on file names to find anything. No re-shooting footage you already have. What you get: → A searchable library of every creative asset your brand has ever produced → Natural language search across video, images, and documents at the same time → Results that show the actual files inline — play videos, view images, read docs → A system that gets smarter every time you add richer descriptions to your assets One free API key. No monthly subscriptions. Runs on your machine. I put together a full playbook with the exact build prompt, the setup process, and DTC/agency use cases to get this running in under 30 minutes. Want the full playbook? > Like this post > Comment "SEARCH" And I'll send it over (must be following so I can DM)

Mike Futia

12,305 views • 7 months ago

📍A local SEO trick every pro should know: Use the UULE parameter to set a precise location for your search results. Adding a UULE parameter to your Google search query lets you see search results from a specific region without needing an extension or being physically there. Here’s how: 1️⃣ Generate a UULE for the location (Find a tool by googling “uule generator”) You will get a code that looks like this: &uule=w+CAIQICIQRWRtb250b24sIENhbmFkYQ 2️⃣ Now run any search in Google. 3️⃣ Look at the URL for your search and replace the last part of it with the UULE parameter. For example: google . com/search?q=sushi+restaurant &uule=w+CAIQICIQRWRtb250b24sIENhbmFkYQ How do you set your search location? #seo #localseo

📍A local SEO trick every pro should know: Use the UULE parameter to set a precise location for your search results. Adding a UULE parameter to your Google search query lets you see search results from a specific region without needing an extension or being physically there. Here’s how: 1️⃣ Generate a UULE for the location (Find a tool by googling “uule generator”) You will get a code that looks like this: &uule=w+CAIQICIQRWRtb250b24sIENhbmFkYQ 2️⃣ Now run any search in Google. 3️⃣ Look at the URL for your search and replace the last part of it with the UULE parameter. For example: google . com/search?q=sushi+restaurant &uule=w+CAIQICIQRWRtb250b24sIENhbmFkYQ How do you set your search location? #seo #localseo

Darren Shaw

28,525 views • 2 years ago

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

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

forloop

226,544 views • 7 months ago

Today we’re announcing Ontology 1, our newest AI model. Perhaps surprisingly, it’s at least 2.7x more accurate than the world’s best ecommerce search engines, and handles queries that have never been possible before. We keep reaching for the edge of what it can do. We haven’t found it yet. Not only that, but it learns on its own with no retraining or fine-tuning. And it’s hallucination-free. It’s a successor architecture for search. Learn how we built it at and check out the benchmarks at Try it at

Today we’re announcing Ontology 1, our newest AI model. Perhaps surprisingly, it’s at least 2.7x more accurate than the world’s best ecommerce search engines, and handles queries that have never been possible before. We keep reaching for the edge of what it can do. We haven’t found it yet. Not only that, but it learns on its own with no retraining or fine-tuning. And it’s hallucination-free. It’s a successor architecture for search. Learn how we built it at and check out the benchmarks at Try it at

Onton

326,827 views • 2 months ago

Introducing BeyondPDF, a smart, free, fully-local (wifi-less) PDF search app for MacOS. "Free" has always connoted to "It's free but we will steal your data"... not anymore. Whats wrong with MacOS's Preview? It's great... but I NEED smart/semantic search. Searching for words is tedious but searching for ideas is wayy easier. I converted a light embedding model from Hugging Face to CoreML and used zero libraries (vectordb + tokenizer is all raw code)... the installer itself is 42mb lol incl. the ML model, so its light and has a reasonable footprint. It's 99% perfect. My goal is to improve perf/UX with every release as more feedback rolls in. I urgently needed this myself and now, you can enjoy it too. Available only on the app store (recommended, linked below) or as a .dmg from my website (also linked).

Introducing BeyondPDF, a smart, free, fully-local (wifi-less) PDF search app for MacOS. "Free" has always connoted to "It's free but we will steal your data"... not anymore. Whats wrong with MacOS's Preview? It's great... but I NEED smart/semantic search. Searching for words is tedious but searching for ideas is wayy easier. I converted a light embedding model from Hugging Face to CoreML and used zero libraries (vectordb + tokenizer is all raw code)... the installer itself is 42mb lol incl. the ML model, so its light and has a reasonable footprint. It's 99% perfect. My goal is to improve perf/UX with every release as more feedback rolls in. I urgently needed this myself and now, you can enjoy it too. Available only on the app store (recommended, linked below) or as a .dmg from my website (also linked).

omkaar

193,685 views • 2 years ago

J-Cal Explains Why Google is UNDERRATED in AI 👀 On E227, the besties discussed Google's value in a post-search world if AI replaces traditional search. @jason broke down why he thinks Google is being slept on: "I think there's a chance that we're underestimating the power of Google's ad network right now." "They have four or five products that are one or two billion users per month. You have YouTube, Google Docs, Android." "They have such a data advantage and such a deep integration into people's lives because they use three or four services, I think Google's gonna figure this out." "It's quite possible that knowing your queries in Gemini, knowing what you're doing in Calendar, knowing what you're watching on YouTube could lead to a stream of more targeted ads that do better and are more valuable." "We've been seeing a number of startups that are figuring out how to use your queries and what you're doing in AI to present to you search results." "So imagine you're doing a Gemini search and on the side of it, it's giving you a rolling list of ads or offers that you might be more interested in." "That could be a better advertising product than even search itself." "I think YouTube search is the place to go all-in." "Right now, when you do a YouTube search, it just gives you 10 links, right? It just gives you that rolling thing." "You should be able to ask a question to YouTube, and you should be able to ask questions to your calendar." "You should be able to say, who have I met with over the last 10 years? Who I'm no longer in touch with and what are they up to?" "And it should do a Gemini search inside of Google Calendar. It's very light right now." "And then if you did that on YouTube, this would train people at the point of pain in a very deep way without sacrificing Google Search queries too aggressively."

J-Cal Explains Why Google is UNDERRATED in AI 👀 On E227, the besties discussed Google's value in a post-search world if AI replaces traditional search. @jason broke down why he thinks Google is being slept on: "I think there's a chance that we're underestimating the power of Google's ad network right now." "They have four or five products that are one or two billion users per month. You have YouTube, Google Docs, Android." "They have such a data advantage and such a deep integration into people's lives because they use three or four services, I think Google's gonna figure this out." "It's quite possible that knowing your queries in Gemini, knowing what you're doing in Calendar, knowing what you're watching on YouTube could lead to a stream of more targeted ads that do better and are more valuable." "We've been seeing a number of startups that are figuring out how to use your queries and what you're doing in AI to present to you search results." "So imagine you're doing a Gemini search and on the side of it, it's giving you a rolling list of ads or offers that you might be more interested in." "That could be a better advertising product than even search itself." "I think YouTube search is the place to go all-in." "Right now, when you do a YouTube search, it just gives you 10 links, right? It just gives you that rolling thing." "You should be able to ask a question to YouTube, and you should be able to ask questions to your calendar." "You should be able to say, who have I met with over the last 10 years? Who I'm no longer in touch with and what are they up to?" "And it should do a Gemini search inside of Google Calendar. It's very light right now." "And then if you did that on YouTube, this would train people at the point of pain in a very deep way without sacrificing Google Search queries too aggressively."

The All-In Podcast

58,275 views • 1 year ago

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or *agentically* create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or agentically create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!

Jerry Liu

77,373 views • 1 year ago

The search for Parker remains our highest priority. In this video, Sgt. Rich Wall, Deputy Operations Chief and Search Manager, provides an update on the significant efforts underway to locate Parker. Over the past week, the CPS has deployed extensive resources, working alongside partner agencies, trained search volunteers and community members to search for Parker and follow up on every possible lead. Search operations continue to be guided by investigative information, lost person behaviour research and established search-management principles. Every effort is being focused on finding the piece of information that could lead us to Parker. We want to thank the hundreds of officers, civilian staff, partner agencies, volunteers and Calgarians who have supported this search. Your cooperation, vigilance and commitment have been nothing short of invaluable and inspiring, and we want to thank you for respecting active search operations and investigative efforts. As we continue this search, we need your help. Please keep your eyes open, review camera footage, check your properties, spread the word and report anything that could assist investigators. No detail is too small. 📹 Watch Sgt. Wall's update. Information? ☎️ CPS: 403-266-1234 🛑 Crime Stoppers YYC 📞 Missing Children Society of Canada (MCSC): 1-800-661-6160 | 📲 MCSC rescu: ⚖ Case #: CA26318270 | 3955

The search for Parker remains our highest priority. In this video, Sgt. Rich Wall, Deputy Operations Chief and Search Manager, provides an update on the significant efforts underway to locate Parker. Over the past week, the CPS has deployed extensive resources, working alongside partner agencies, trained search volunteers and community members to search for Parker and follow up on every possible lead. Search operations continue to be guided by investigative information, lost person behaviour research and established search-management principles. Every effort is being focused on finding the piece of information that could lead us to Parker. We want to thank the hundreds of officers, civilian staff, partner agencies, volunteers and Calgarians who have supported this search. Your cooperation, vigilance and commitment have been nothing short of invaluable and inspiring, and we want to thank you for respecting active search operations and investigative efforts. As we continue this search, we need your help. Please keep your eyes open, review camera footage, check your properties, spread the word and report anything that could assist investigators. No detail is too small. 📹 Watch Sgt. Wall's update. Information? ☎️ CPS: 403-266-1234 🛑 Crime Stoppers YYC 📞 Missing Children Society of Canada (MCSC): 1-800-661-6160 | 📲 MCSC rescu: ⚖ Case #: CA26318270 | 3955

Calgary Police

26,494 views • 2 months ago

Mark Zuckerberg to new-hire Aditya Agarwal : “If I can build Facebook you can build a search engine” Aditya recalls starting at Facebook in 2005. A few weeks into his new role, Mark Zuckerberg comes up to him and suggests he build a search engine: “When people come to Facebook, the first thing they want to do is search for people.” Aditya’s first reaction was that search was a really important thing to get right and he had never built a search engine - wouldn’t it make more sense to just hire somebody from Google or Yahoo to do it? Mark replied: “If I can build Facebook, you can build a search engine.” And he was right - Aditya did end up building search for Facebook. This interaction also left a lasting impression on Aditya: “All of us can build whatever we put our minds to. And this is the culture that for me still defines Facebook - there is this hacker, can-do, total-ownership culture. If I could tell every startup in the world to take one thing, it would be you can do whatever you want as long as you put your mind to it. It’s probably easier than you think.” Video source: South Park Commons (2024)

Mark Zuckerberg to new-hire Aditya Agarwal : “If I can build Facebook you can build a search engine” Aditya recalls starting at Facebook in 2005. A few weeks into his new role, Mark Zuckerberg comes up to him and suggests he build a search engine: “When people come to Facebook, the first thing they want to do is search for people.” Aditya’s first reaction was that search was a really important thing to get right and he had never built a search engine - wouldn’t it make more sense to just hire somebody from Google or Yahoo to do it? Mark replied: “If I can build Facebook, you can build a search engine.” And he was right - Aditya did end up building search for Facebook. This interaction also left a lasting impression on Aditya: “All of us can build whatever we put our minds to. And this is the culture that for me still defines Facebook - there is this hacker, can-do, total-ownership culture. If I could tell every startup in the world to take one thing, it would be you can do whatever you want as long as you put your mind to it. It’s probably easier than you think.” Video source: South Park Commons (2024)

Startup Archive

136,570 views • 7 months ago

We’re officially a YOUnicorn! 🦄 Excited to share that You.com just raised $100M Series C at a $1.5B valuation, led by Cox Enterprises. We’ve been heads down building the search infrastructure for the AI and agent future. Soon there will be more AI agents using the web than humans, but today's search wasn't built for this. Agents need deep, contextual information from both public web and internal private data to make real decisions. Our web search API delivers the most up-to-date, accurate, and fastest search results for LLMs and agents. Real benchmarks show we consistently outperform the competition on accuracy and speed while staying cost-effective. Today, we’re answering over 1 billion queries every month across enterprises like DuckDuckGo, Windsurf, Harvey, and many others. There is no other startup of recent years at this scale. Grateful to our wonderful employees, customers, partners, and investors who believe in our vision. The agentic era is here - let's build it together. Try our LLM search APIs.

We’re officially a YOUnicorn! 🦄 Excited to share that You.com just raised $100M Series C at a $1.5B valuation, led by Cox Enterprises. We’ve been heads down building the search infrastructure for the AI and agent future. Soon there will be more AI agents using the web than humans, but today's search wasn't built for this. Agents need deep, contextual information from both public web and internal private data to make real decisions. Our web search API delivers the most up-to-date, accurate, and fastest search results for LLMs and agents. Real benchmarks show we consistently outperform the competition on accuracy and speed while staying cost-effective. Today, we’re answering over 1 billion queries every month across enterprises like DuckDuckGo, Windsurf, Harvey, and many others. There is no other startup of recent years at this scale. Grateful to our wonderful employees, customers, partners, and investors who believe in our vision. The agentic era is here - let's build it together. Try our LLM search APIs.

Richard Socher

63,709 views • 1 year ago

Finally, a database can generate its own embeddings now. When you add semantic search to an app, the standard step is to wire up an external embedding service, sync the vectors to a separate store, and write glue to keep everything updated as data changes. While this is a standard setup, problems show up later when your data changes, but your pipeline has already run, and search quality starts degrading in ways that are hard to pin down because nothing is explicitly broken. MongoDB Atlas handles this with auto-embedding. You point an index at a text field, specify a Voyage AI model, and Atlas generates the vectors inside the database. When a document changes, it re-embeds itself automatically, so that the search always stays grounded to the current context. I tested this against MongoDB's sample movies collection, 21,000 plots indexed with one config. A plain English query about dystopian machine-controlled futures returned semantically relevant results, despite having no keyword overlap. You can try it yourself here: One index config replaced the embedding service, the vector store, and the sync layer you used to maintain separately. The video below depicts this in action, and I worked with the MongoDB team to put this together. I have also put together a full LLM engineering roadmap covering what it actually takes to build and ship production AI systems in 2026. Read it below.

Finally, a database can generate its own embeddings now. When you add semantic search to an app, the standard step is to wire up an external embedding service, sync the vectors to a separate store, and write glue to keep everything updated as data changes. While this is a standard setup, problems show up later when your data changes, but your pipeline has already run, and search quality starts degrading in ways that are hard to pin down because nothing is explicitly broken. MongoDB Atlas handles this with auto-embedding. You point an index at a text field, specify a Voyage AI model, and Atlas generates the vectors inside the database. When a document changes, it re-embeds itself automatically, so that the search always stays grounded to the current context. I tested this against MongoDB's sample movies collection, 21,000 plots indexed with one config. A plain English query about dystopian machine-controlled futures returned semantically relevant results, despite having no keyword overlap. You can try it yourself here: One index config replaced the embedding service, the vector store, and the sync layer you used to maintain separately. The video below depicts this in action, and I worked with the MongoDB team to put this together. I have also put together a full LLM engineering roadmap covering what it actually takes to build and ship production AI systems in 2026. Read it below.

Avi Chawla

14,463 views • 2 months ago

How do search teams cover large areas while ensuring no stone is left unturned? In this video, one of our officers explains the various search methods we and our partners are using in the search for Parker. These efforts are supported by specialized and traditional techniques and teams that include coordinated ground searches, RPAS (drone) operations and dedicated canine teams. These resources help search areas that may be difficult to access on foot and provide additional perspectives as teams continue to search for Parker. The terrain and current heat conditions have made this work particularly challenging. In some areas, searchers are positioned closely together to ensure no potential clue, evidence or point of interest is overlooked. Every search operation is carefully planned using investigative information, search management principles and lost person behaviour research. Together, officers, partner agencies and trained search volunteers continue working tirelessly toward one goal: finding Parker. We remain grateful for the unwavering commitment of everyone involved in this search and for the continued support of our community. If you have information that may assist investigators, no matter how small it may seem, please report it to police. Information? ☎️ CPS: 403-266-1234 🛑 Crime Stoppers YYC 📞 Missing Children Society of Canada (MCSC): 1-800-661-6160 | 📲 MCSC rescu: ⚖ Case #: CA26318270 | 3955

How do search teams cover large areas while ensuring no stone is left unturned? In this video, one of our officers explains the various search methods we and our partners are using in the search for Parker. These efforts are supported by specialized and traditional techniques and teams that include coordinated ground searches, RPAS (drone) operations and dedicated canine teams. These resources help search areas that may be difficult to access on foot and provide additional perspectives as teams continue to search for Parker. The terrain and current heat conditions have made this work particularly challenging. In some areas, searchers are positioned closely together to ensure no potential clue, evidence or point of interest is overlooked. Every search operation is carefully planned using investigative information, search management principles and lost person behaviour research. Together, officers, partner agencies and trained search volunteers continue working tirelessly toward one goal: finding Parker. We remain grateful for the unwavering commitment of everyone involved in this search and for the continued support of our community. If you have information that may assist investigators, no matter how small it may seem, please report it to police. Information? ☎️ CPS: 403-266-1234 🛑 Crime Stoppers YYC 📞 Missing Children Society of Canada (MCSC): 1-800-661-6160 | 📲 MCSC rescu: ⚖ Case #: CA26318270 | 3955

Calgary Police

19,285 views • 2 months ago

Today we are announcing Keenable AI, an AI-native index of the best human knowledge we have, starting with the open web. AI seems to know just about everything until you ask it about something you know deeply. The answer isn’t wrong, but it's just very average. We started Keenable to fix this problem: every model and every agent should be able to query, reason over, and continuously learn from the living web. Backed by a $26M Seed from Accel and Conviction. Built by the team that took on Google at Yandex Search, with researchers and engineers from Amazon AGI, X, and Perplexity. The Web Search API and Web Query Language for AI are live now. Together they make the web queryable at AI scale. Both are free until end of September. Seven days of benchmarks, stories, and launches ahead. Let your agents search.

Today we are announcing Keenable AI, an AI-native index of the best human knowledge we have, starting with the open web. AI seems to know just about everything until you ask it about something you know deeply. The answer isn’t wrong, but it's just very average. We started Keenable to fix this problem: every model and every agent should be able to query, reason over, and continuously learn from the living web. Backed by a $26M Seed from Accel and Conviction. Built by the team that took on Google at Yandex Search, with researchers and engineers from Amazon AGI, X, and Perplexity. The Web Search API and Web Query Language for AI are live now. Together they make the web queryable at AI scale. Both are free until end of September. Seven days of benchmarks, stories, and launches ahead. Let your agents search.

Andrey Styskin

553,424 views • 1 month ago

Introducing Sharpe Search: On-Chain Search AI Agent Powered by Hive Intelligence We’re thrilled to announce the launch of Sharpe Search, a crypto search AI agent powered by Hive Intelligence Designed to simplify blockchain data interaction, Sharpe Search represents a significant step toward making crypto more accessible and actionable for users at every level. Sharpe Search leverages Hive Intelligence’s advanced search API to provide real-time, actionable insights across the blockchain ecosystem. Here’s a detailed look at what Sharpe Search is, how it works: What Is Sharpe Search? At its core, Sharpe Search is an AI agent purpose-built for querying and analyzing on-chain data. It takes the complexity out of blockchain exploration by enabling users to ask questions in plain language and receive detailed, accurate responses. Whether you’re looking to monitor wallet activity, track portfolio positions, or analyze transaction history, Sharpe Search ensures that the answers are at your fingertips—accurate, comprehensive, and delivered instantly. How Does Sharpe Search Work? Sharpe Search is powered by Hive Intelligence, a search engine API designed to make blockchain data easily accessible and AI-ready. Here’s a breakdown of how it enables Sharpe Search to function effectively: 1. LLM-Optimized Query Processing Sharpe Search leverages Hive Intelligence's optimized responses for large language models. This ensures that AI agents can process blockchain data in a structured format, delivering precise answers to complex user queries. 2. Natural Language Interaction Forget the need for technical knowledge. Sharpe Search supports natural language queries, making it as simple as typing: - “What tokens are in my wallet? Am I eligible for any airdrop I haven't claimed yet?” - “Check me my last 100 transactions, tell me if I interacted with any protocol with recent hacks” - “Track my wallet activity over the past month, suggest optimised portfolio based on best stable yields available” 3. Real-Time Insights Across Multi-Chains Using Hive Intelligence, Sharpe Search connects to over 20 chains and 5000+ Protocols. This real-time access ensures that the AI agent provides up-to-date and actionable insights, no matter how dynamic the blockchain environment. 4. Unified API Access Sharpe Search consolidates fragmented blockchain data through Hive’s unified API. Instead of dealing with multiple integrations, Sharpe Search uses a single access point to aggregate and query data, reducing complexity for both users and developers. Technical Depth: The AI Agent Advantage Sharpe Search's design philosophy revolves around the principle of creating an intuitive, AI-driven experience. Here’s what makes its technology stand out: Data Indexing and Aggregation: Hive Intelligence employs advanced indexing algorithms to aggregate data from multiple chains. This ensures that Sharpe Search can retrieve information within milliseconds, even when querying vast datasets. Dynamic Updates: Blockchain data is volatile. Sharpe Search processes dynamic updates in real time, enabling users to act on the most recent metrics, transactions, and balances without delays. Contextual Understanding: The AI agent parses natural language queries and contextualizes them to blockchain-specific scenarios. For instance, when querying “Show portfolio details,” Sharpe Search understands the underlying requirements—fetching wallet holdings, token values, and current positions. Hive Intelligence: The Backbone of Sharpe Search While Sharpe Search takes center stage, Hive Intelligence provides the critical infrastructure to make it all possible. Its LLM-ready responses and multi-chain support ensure that Sharpe Search operates at the forefront of blockchain data accessibility. By launching Hive Intelligence through Sharpe Launchpad, Sharpe reinforces its commitment to supporting innovation in the blockchain space. Hive’s infrastructure not only powers Sharpe Search but also lays the groundwork for future AI agents to thrive in the ecosystem. What’s Next for Sharpe Search? Currently in invite-only access, Sharpe Search is preparing for a broader public release. Future updates will include: - Expanded Blockchain Coverage: More chains and protocols will be added. - Enhanced Query Flexibility: Even more advanced natural language capabilities. Stay tuned for the public launch and get ready to explore crypto like never before!

Introducing Sharpe Search: On-Chain Search AI Agent Powered by Hive Intelligence We’re thrilled to announce the launch of Sharpe Search, a crypto search AI agent powered by Hive Intelligence Designed to simplify blockchain data interaction, Sharpe Search represents a significant step toward making crypto more accessible and actionable for users at every level. Sharpe Search leverages Hive Intelligence’s advanced search API to provide real-time, actionable insights across the blockchain ecosystem. Here’s a detailed look at what Sharpe Search is, how it works: What Is Sharpe Search? At its core, Sharpe Search is an AI agent purpose-built for querying and analyzing on-chain data. It takes the complexity out of blockchain exploration by enabling users to ask questions in plain language and receive detailed, accurate responses. Whether you’re looking to monitor wallet activity, track portfolio positions, or analyze transaction history, Sharpe Search ensures that the answers are at your fingertips—accurate, comprehensive, and delivered instantly. How Does Sharpe Search Work? Sharpe Search is powered by Hive Intelligence, a search engine API designed to make blockchain data easily accessible and AI-ready. Here’s a breakdown of how it enables Sharpe Search to function effectively: 1. LLM-Optimized Query Processing Sharpe Search leverages Hive Intelligence's optimized responses for large language models. This ensures that AI agents can process blockchain data in a structured format, delivering precise answers to complex user queries. 2. Natural Language Interaction Forget the need for technical knowledge. Sharpe Search supports natural language queries, making it as simple as typing: - “What tokens are in my wallet? Am I eligible for any airdrop I haven't claimed yet?” - “Check me my last 100 transactions, tell me if I interacted with any protocol with recent hacks” - “Track my wallet activity over the past month, suggest optimised portfolio based on best stable yields available” 3. Real-Time Insights Across Multi-Chains Using Hive Intelligence, Sharpe Search connects to over 20 chains and 5000+ Protocols. This real-time access ensures that the AI agent provides up-to-date and actionable insights, no matter how dynamic the blockchain environment. 4. Unified API Access Sharpe Search consolidates fragmented blockchain data through Hive’s unified API. Instead of dealing with multiple integrations, Sharpe Search uses a single access point to aggregate and query data, reducing complexity for both users and developers. Technical Depth: The AI Agent Advantage Sharpe Search's design philosophy revolves around the principle of creating an intuitive, AI-driven experience. Here’s what makes its technology stand out: Data Indexing and Aggregation: Hive Intelligence employs advanced indexing algorithms to aggregate data from multiple chains. This ensures that Sharpe Search can retrieve information within milliseconds, even when querying vast datasets. Dynamic Updates: Blockchain data is volatile. Sharpe Search processes dynamic updates in real time, enabling users to act on the most recent metrics, transactions, and balances without delays. Contextual Understanding: The AI agent parses natural language queries and contextualizes them to blockchain-specific scenarios. For instance, when querying “Show portfolio details,” Sharpe Search understands the underlying requirements—fetching wallet holdings, token values, and current positions. Hive Intelligence: The Backbone of Sharpe Search While Sharpe Search takes center stage, Hive Intelligence provides the critical infrastructure to make it all possible. Its LLM-ready responses and multi-chain support ensure that Sharpe Search operates at the forefront of blockchain data accessibility. By launching Hive Intelligence through Sharpe Launchpad, Sharpe reinforces its commitment to supporting innovation in the blockchain space. Hive’s infrastructure not only powers Sharpe Search but also lays the groundwork for future AI agents to thrive in the ecosystem. What’s Next for Sharpe Search? Currently in invite-only access, Sharpe Search is preparing for a broader public release. Future updates will include: - Expanded Blockchain Coverage: More chains and protocols will be added. - Enhanced Query Flexibility: Even more advanced natural language capabilities. Stay tuned for the public launch and get ready to explore crypto like never before!

Sharpe AI

263,308 views • 1 year ago