正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

X bookmarks, but: - Vector + text search (username + name + content) - Sort + filter by engagement, post date, media

matt palmer

42,659 subscribers

95,560 次观看 • 1 年前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

All markets, every chain, one view. But "all" can be a lot 🤯 So we built filters to cut through it: • Select chains • Filter by debt token, collateral, or maturity • Search by name • Filter by tag Multichain without the clutter.

All markets, every chain, one view. But "all" can be a lot 🤯 So we built filters to cut through it: • Select chains • Filter by debt token, collateral, or maturity • Search by name • Filter by tag Multichain without the clutter.

TermMax | Fixed Rate Borrowing & Lending

103,678 次观看 • 1 个月前

CLAUDE CAN NOW SEARCH ALL OF YOUTUBE LIVE! → sort by views, upload date, or rating → filter by last hour / day / week / years → pulls realtime yt data, not a database snapshot the future of yt research is here. live now inside algrow mcp →

CLAUDE CAN NOW SEARCH ALL OF YOUTUBE LIVE! → sort by views, upload date, or rating → filter by last hour / day / week / years → pulls realtime yt data, not a database snapshot the future of yt research is here. live now inside algrow mcp →

sam

13,444 次观看 • 3 个月前

experimenting with color-coded flow fields to map personal interests: embedded my x bookmarks into 33 topic clusters, each acting as a gravitational attractor; their mass is calculated by cluster size, recency, or public engagement.

experimenting with color-coded flow fields to map personal interests: embedded my x bookmarks into 33 topic clusters, each acting as a gravitational attractor; their mass is calculated by cluster size, recency, or public engagement.

Kat ⊷ the Poet Engineer

58,114 次观看 • 2 个月前

Grok is telling me that moving forward on X, Native video-first content on X (direct X uploads) gets 10× more distribution than text, photos or linked media. Ok, so let's give it a try.

Grok is telling me that moving forward on X, Native video-first content on X (direct X uploads) gets 10× more distribution than text, photos or linked media. Ok, so let's give it a try.

Tracy Lynne 💕

25,456 次观看 • 3 个月前

Someone is going to make a lot of money building niche versions of Canva - Go to ahrefs - search "canva .com/apps" - Filter KD < 20 - Sort by value ($$$) And find endless micro SaaS ideas - Vcard QR code generator - AI sticker generator - AI Coloring book generator - Line art generator and more..

Someone is going to make a lot of money building niche versions of Canva - Go to ahrefs - search "canva .com/apps" - Filter KD < 20 - Sort by value ($$$) And find endless micro SaaS ideas - Vcard QR code generator - AI sticker generator - AI Coloring book generator - Line art generator and more..

Ayush 🙏

120,533 次观看 • 10 个月前

📢 Social Mining on X — Tip #7: Native Media Over Clickbait Visuals boost dwell time, but X penalizes generic stock photos used as bait. The algorithm prioritizes native video and authentic screenshots that directly prove or illustrate your text.👇

📢 Social Mining on X — Tip #7: Native Media Over Clickbait Visuals boost dwell time, but X penalizes generic stock photos used as bait. The algorithm prioritizes native video and authentic screenshots that directly prove or illustrate your text.👇

DAO Labs

15,096 次观看 • 6 天前

First audio post in a looong time, with new equipment. My account isn't fully ready yet, but have this until then! 💋🖤♠️ Image censor, text & audio by me! Art by HOURAKU

Sensitive content

First audio post in a looong time, with new equipment. My account isn't fully ready yet, but have this until then! 💋🖤♠️ Image censor, text & audio by me! Art by HOURAKU

Minako // Temp Hiatus

15,542 次观看 • 1 年前

In this mesmerizing y=Ax video, eigenvectors glow with brilliance! As you rotate the vector x, Ax traces the ellipse perfectly. But the eigenvector lights up—no rotation at all, just pure scaling by its eigenvalue!

In this mesmerizing y=Ax video, eigenvectors glow with brilliance! As you rotate the vector x, Ax traces the ellipse perfectly. But the eigenvector lights up—no rotation at all, just pure scaling by its eigenvalue!

Mathematica

68,135 次观看 • 3 个月前

What makes people stop scrolling on X? What drives engagement? What triggers the algorithm? For the past year, we’ve reverse-engineered hundreds of viral tweets from my account and scientifically studied the X algorithm. We embedded every insight we gained into SurgeKit. It is a powerful tool that helps you write better on X, post smarter, and grow faster. Used by top creators. Built by real practitioners. Fed with virality data from my own content. Now in public beta →

What makes people stop scrolling on X? What drives engagement? What triggers the algorithm? For the past year, we’ve reverse-engineered hundreds of viral tweets from my account and scientifically studied the X algorithm. We embedded every insight we gained into SurgeKit. It is a powerful tool that helps you write better on X, post smarter, and grow faster. Used by top creators. Built by real practitioners. Fed with virality data from my own content. Now in public beta →

Mario Nawfal

242,676 次观看 • 1 年前

this is the easiest way to find viral content formats. i built a library that: > pulls trending slides & videos > shows hook + caption > tracks engagement (views, likes, shares) no more scrolling tiktok for hours to find inspo. just filter by niche & copy what works

this is the easiest way to find viral content formats. i built a library that: > pulls trending slides & videos > shows hook + caption > tracks engagement (views, likes, shares) no more scrolling tiktok for hours to find inspo. just filter by niche & copy what works

Fekri

13,623 次观看 • 6 个月前

When you realize that Elon Musk can be the top diablo player, run 7 companies, fix the government, and still have time to post memes on X . But she's " too busy " to text you back

When you realize that Elon Musk can be the top diablo player, run 7 companies, fix the government, and still have time to post memes on X . But she's " too busy " to text you back

naiive

1,242,928 次观看 • 1 年前

SAY HER NAME - Amelia Carter 29 years old. Burned alive n subway by an illegal alien (the instagram below states they are her parents). Media refuses to post her name/face and tried to smear her by saying she was drunk or homeless and was seated by empty alcohol bottles. The subway is aways filthy.

SAY HER NAME - Amelia Carter 29 years old. Burned alive n subway by an illegal alien (the instagram below states they are her parents). Media refuses to post her name/face and tried to smear her by saying she was drunk or homeless and was seated by empty alcohol bottles. The subway is aways filthy.

XYZ

303,288 次观看 • 1 年前

🔥🚨DEVELOPING: This leaked footage of a Chinese bot farm is going viral. Bot farms are where multiple devices connected to the internet with different social media profiles engage in a targeted post to boost its engagement. I wonder which X creator has a relationship with them.

🔥🚨DEVELOPING: This leaked footage of a Chinese bot farm is going viral. Bot farms are where multiple devices connected to the internet with different social media profiles engage in a targeted post to boost its engagement. I wonder which X creator has a relationship with them.

Dom Lucre | Breaker of Narratives

3,068,791 次观看 • 2 年前

Making a ‘YGNGG DEFENCE GC’ and look the rules : — stan ‘YG NEXT MONSTER’ ofcourse — active on X and support YGNGG content — no fanwar and no setup account — support all member YGNGG for now, i will only select 20-30 accounts, follow this account and don't forget to retweet this post, then comment with your username account in here !!

Making a ‘YGNGG DEFENCE GC’ and look the rules : — stan ‘YG NEXT MONSTER’ ofcourse — active on X and support YGNGG content — no fanwar and no setup account — support all member YGNGG for now, i will only select 20-30 accounts, follow this account and don't forget to retweet this post, then comment with your username account in here !!

NEXTMONSTER PICS

19,478 次观看 • 1 年前

Big moment for Postgres! Search has always been Postgres' weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.

Big moment for Postgres! Search has always been Postgres' weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.

Akshay 🚀

215,344 次观看 • 5 个月前

Newcastle reserves looking the part. No doubt this meaningless pre season friendly result against a 3rd string will be lauded as some sort of achievement by the media propaganda wing of Celtic but real football afficionados know it means nothing.

Newcastle reserves looking the part. No doubt this meaningless pre season friendly result against a 3rd string will be lauded as some sort of achievement by the media propaganda wing of Celtic but real football afficionados know it means nothing.

Der Röhl Souness

289,186 次观看 • 1 年前

[MEDIA SUPPORT] PREVIEW: TIMES SQUARE BILLBOARD LED FOR MARTIN 📍Location: Times Square, 1560 Broadway, NYC, USA ⭐️Date: 20/3/2026 (GMT -5) 💥Frequency: 22 plays per date. 💫Time: 14th minute each hour Livestream link: Photo by mar.univrs Project: Shades of Martin n0.1 : Red By soomi Collab with @toobadsaltsad and @yapperoniez For Martin Edwards, I want the whole world to know your name #MARTIN #CORTIS #마틴 #코르티스

[MEDIA SUPPORT] PREVIEW: TIMES SQUARE BILLBOARD LED FOR MARTIN 📍Location: Times Square, 1560 Broadway, NYC, USA ⭐️Date: 20/3/2026 (GMT -5) 💥Frequency: 22 plays per date. 💫Time: 14th minute each hour Livestream link: Photo by mar.univrs Project: Shades of Martin n0.1 : Red By soomi Collab with @toobadsaltsad and @yapperoniez For Martin Edwards, I want the whole world to know your name #MARTIN #CORTIS #마틴 #코르티스

mar.univrs

36,300 次观看 • 4 个月前

Regarding the Eric Trump / Daniel Cormier “text scandal”, I am open to being convinced otherwise, but I do not believe for one second that Eric Trump would text something so stupid to Daniel Cormier. It’s laughably stupid on its face to think that Eric Trump would ask a UFC commentator if any of the fights are “rigged”. That he would ask it in writing. And that he would not, for example, just pick up the phone and call Dana White or Joe Rogan himself. That said, I just want to understand what happened. Daniel Cormier said he was hacked. Is that to say he was hacked at the text level, or the X post level? Did he in fact make the post, and delete it? If he made the post, did he do it as a joke to illustrate how absurd the text hack was, but realized how the post could be misinterpreted as real? Or did someone make the post from his X account he subsequently deleted it. I know there are some who are going to say he made the post in earnest, thinking the text messages were real, intending to call out the “corruption”, and he has since been threatened, deleted the post, and claimed “hack”, etc. I can tell you exactly why I do not believe, even if he made the post, he did it believing the text message was real, intending to call out the “corruption”. If Cormier seriously thought the text messages were real, he would understand that by posting it publicly, it would literally destroy the UFC, his livelihood and his legacy - in addition to the legacy of everyone who has ever competed in the UFC. There is no realm of the universe in which even if it were in fact a real text that he actually received from Eric Trump, he would post it publicly. Because it would mean the end of the UFC. I just want to know if he actually made the post from his X account, or if the entire post was the result of a hack (hence the subsequent deleting of the post). Serious and sincere questions for clarity that would benefit everyone Eric Trump

Regarding the Eric Trump / Daniel Cormier “text scandal”, I am open to being convinced otherwise, but I do not believe for one second that Eric Trump would text something so stupid to Daniel Cormier. It’s laughably stupid on its face to think that Eric Trump would ask a UFC commentator if any of the fights are “rigged”. That he would ask it in writing. And that he would not, for example, just pick up the phone and call Dana White or Joe Rogan himself. That said, I just want to understand what happened. Daniel Cormier said he was hacked. Is that to say he was hacked at the text level, or the X post level? Did he in fact make the post, and delete it? If he made the post, did he do it as a joke to illustrate how absurd the text hack was, but realized how the post could be misinterpreted as real? Or did someone make the post from his X account he subsequently deleted it. I know there are some who are going to say he made the post in earnest, thinking the text messages were real, intending to call out the “corruption”, and he has since been threatened, deleted the post, and claimed “hack”, etc. I can tell you exactly why I do not believe, even if he made the post, he did it believing the text message was real, intending to call out the “corruption”. If Cormier seriously thought the text messages were real, he would understand that by posting it publicly, it would literally destroy the UFC, his livelihood and his legacy - in addition to the legacy of everyone who has ever competed in the UFC. There is no realm of the universe in which even if it were in fact a real text that he actually received from Eric Trump, he would post it publicly. Because it would mean the end of the UFC. I just want to know if he actually made the post from his X account, or if the entire post was the result of a hack (hence the subsequent deleting of the post). Serious and sincere questions for clarity that would benefit everyone Eric Trump

Viva Frei

30,167 次观看 • 29 天前

Vector Database by Hand ✍️ Vector databases are revolutionizing how we search and analyze complex data. They have become the backbone of Retrieval Augmented Generation (#RAG). How do vector databases work? [1] Given ↳ A dataset of three sentences, each has 3 words (or tokens) ↳ In practice, a dataset may contain millions or billions of sentences. The max number of tokens may be tens of thousands (e.g., 32,768 mistral-7b). Process "how are you" [2] 🟨 Word Embeddings ↳ For each word, look up corresponding word embedding vector from a table of 22 vectors, where 22 is the vocabulary size. ↳ In practice, the vocabulary size can be tens of thousands. The word embedding dimensions are in the thousands (e.g., 1024, 4096) [3] 🟩 Encoding ↳ Feed the sequence of word embeddings to an encoder to obtain a sequence of feature vectors, one per word. ↳ Here, the encoder is a simple one layer perceptron (linear layer + ReLU) ↳ In practice, the encoder is a transformer or one of its many variants. [4] 🟩 Mean Pooling ↳ Merge the sequence of feature vectors into a single vector using "mean pooling" which is to average across the columns. ↳ The result is a single vector. We often call it "text embeddings" or "sentence embeddings." ↳ Other pooling techniques are possible, such as CLS. But mean pooling is the most common. [5] 🟦 Indexing ↳ Reduce the dimensions of the text embedding vector by a projection matrix. The reduction rate is 50% (4->2). ↳ In practice, the values in this projection matrix is much more random. ↳ The purpose is similar to that of hashing, which is to obtain a short representation to allow faster comparison and retrieval. ↳ The resulting dimension-reduced index vector is saved in the vector storage. [6] Process "who are you" ↳ Repeat [2]-[5] [7] Process "who am I" ↳ Repeat [2]-[5] Now we have indexed our dataset in the vector database. [8] 🟥 Query: "am I you" ↳ Repeat [2]-[5] ↳ The result is a 2-d query vector. [9] 🟥 Dot Products ↳ Take dot product between the query vector and database vectors. They are all 2-d. ↳ The purpose is to use dot product to estimate similarity. ↳ By transposing the query vector, this step becomes a matrix multiplication. [10] 🟥 Nearest Neighbor ↳ Find the largest dot product by linear scan. ↳ The sentence with the highest dot product is "who am I" ↳ In practice, because scanning billions of vectors is slow, we use an Approximate Nearest Neighbor (ANN) algorithm like the Hierarchical Navigable Small Worlds (HNSW).

Vector Database by Hand ✍️ Vector databases are revolutionizing how we search and analyze complex data. They have become the backbone of Retrieval Augmented Generation (#RAG). How do vector databases work? [1] Given ↳ A dataset of three sentences, each has 3 words (or tokens) ↳ In practice, a dataset may contain millions or billions of sentences. The max number of tokens may be tens of thousands (e.g., 32,768 mistral-7b). Process "how are you" [2] 🟨 Word Embeddings ↳ For each word, look up corresponding word embedding vector from a table of 22 vectors, where 22 is the vocabulary size. ↳ In practice, the vocabulary size can be tens of thousands. The word embedding dimensions are in the thousands (e.g., 1024, 4096) [3] 🟩 Encoding ↳ Feed the sequence of word embeddings to an encoder to obtain a sequence of feature vectors, one per word. ↳ Here, the encoder is a simple one layer perceptron (linear layer + ReLU) ↳ In practice, the encoder is a transformer or one of its many variants. [4] 🟩 Mean Pooling ↳ Merge the sequence of feature vectors into a single vector using "mean pooling" which is to average across the columns. ↳ The result is a single vector. We often call it "text embeddings" or "sentence embeddings." ↳ Other pooling techniques are possible, such as CLS. But mean pooling is the most common. [5] 🟦 Indexing ↳ Reduce the dimensions of the text embedding vector by a projection matrix. The reduction rate is 50% (4->2). ↳ In practice, the values in this projection matrix is much more random. ↳ The purpose is similar to that of hashing, which is to obtain a short representation to allow faster comparison and retrieval. ↳ The resulting dimension-reduced index vector is saved in the vector storage. [6] Process "who are you" ↳ Repeat [2]-[5] [7] Process "who am I" ↳ Repeat [2]-[5] Now we have indexed our dataset in the vector database. [8] 🟥 Query: "am I you" ↳ Repeat [2]-[5] ↳ The result is a 2-d query vector. [9] 🟥 Dot Products ↳ Take dot product between the query vector and database vectors. They are all 2-d. ↳ The purpose is to use dot product to estimate similarity. ↳ By transposing the query vector, this step becomes a matrix multiplication. [10] 🟥 Nearest Neighbor ↳ Find the largest dot product by linear scan. ↳ The sentence with the highest dot product is "who am I" ↳ In practice, because scanning billions of vectors is slow, we use an Approximate Nearest Neighbor (ANN) algorithm like the Hierarchical Navigable Small Worlds (HNSW).

Tom Yeh

191,974 次观看 • 2 年前

Lots of new people here . Hey yall !! My name is Juné but people on X calling me Auntie . I post picks and Pics on my page . I’m a sweetheart with a low tolerance for bs . I’ll block you in 2.5 seconds . Welcome

Lots of new people here . Hey yall !! My name is Juné but people on X calling me Auntie . I post picks and Pics on my page . I’m a sweetheart with a low tolerance for bs . I’ll block you in 2.5 seconds . Welcome

Juné

250,408 次观看 • 8 个月前