•twitter16078
listening to
timeline
16078
mentions
tracked
tracked
net sentiment
+24%
5063 positive
9855 neutral
1160 negative
volume & sentiment over time
Sep 30 – Oct 16, 2026 · Daily
sources
most discussed
—
active days
16
mentions
Showing 12651–12675 of 16078 mentions
-
• twitter 1w neutralT 5875 - rehearsal T 5875 - rehearsalview source ↗
-
• twitter 1w neutralhttps://t.co/3QTITCtlUZ https://t.co/3QTITCtlUZview source ↗
-
• twitter 1w neutralRT @liu8in: launch anxiety is real this weekend we'll be launching a series of products starting monday thru eom i'm very very excited, b… RT @liu8in: launch anxiety is real this weekend we'll be launching a series of products starting monday thru eom i'm very very excited, b…view source ↗
-
• twitter 1w neutralwait it was supposed to be the other way around (this is incredibly sick btw) https://t.co/0cXuafwctE wait it was supposed to be the other way around (this is incredibly sick btw) https://t.co/0cXuafwctEview source ↗
-
• twitter 1w positiveIf I had 1 month to build my Portfolio Project which will get me hired as an AI RAG Engineer, I would do these, starting from basics to advance: 1) Build your vectordb: Arrange a dataset with thousands of unstructured files. You can get it from any open source repository or platform. Now before chunking, you choose ty… If I had 1 month to build my Portfolio Project which will get me hired as an AI RAG Engineer, I would do these, starting from basics to advance: 1) Build your vectordb: Arrange a dataset with thousands of unstructured files. You can get it from any open source repository or platform. Now before chunking, you choose type of vectordb you require. Do you need a dedicated vectordb or pg vector extension? This should be a business impact based decision. If you need Vectordb + Crud operations in one database then go with pgvector extension. If you don't have crud operations in your business and require a high scalable vectordb then go with a dedicated vectordb. 2) Engineer the chunking strategy: The first and foremost strategy of any RAG pipeline is chunking. There are various types of chunking strategies like paragraph chunking, paragraph with overlap chunking, document layout aware based chunking, LLM based reasoning chunking, etc. For the files which contains text + images + tables, you can opt for either document layout aware based chunking or build a pipeline to process three different chunking for this three different requirements. 3) Build and Evaluate your first retriever like a real engineer: Choose your retriever strategy, either it could be semantic or keyword based or both. Now question is how you gonna choose? It could be usecase wise too, if that dataset has some keywords which is hard to retrieve semantically then use hybrid approch. In interview they will ask how do you know that semantically it will be harder to fetch those?? To answer this question like a True Real Engineer, you do experiments with this two different retriever strategies semantic vs hybrid. You take 1 eval dataset, and example queries, and give those examples queries to retrieval to fetch chunks from vectordb and then you evaluate those chunks with eval dataset with metrices like Precision, Recall, MRR, Hitrate, Context Recall and Context Relevance. Now you make decisions based on thview source ↗
-
• twitter 1w positiveDon't be affected by criticism. Positive or negative, take them in your stride. Know that the level of criticism rises with your worth. Don't be affected by criticism. Positive or negative, take them in your stride. Know that the level of criticism rises with your worth.view source ↗
-
• twitter 1w neutralRT @gr00vyfairy: real. @CueAgents https://t.co/nT6FGg1UB0 RT @gr00vyfairy: real. @CueAgents https://t.co/nT6FGg1UB0view source ↗
-
• twitter 1w neutralhttps://t.co/izW2Jd0Fkn https://t.co/izW2Jd0Fknview source ↗
-
• twitter 1w neutralhttps://t.co/DMjVyjR9V7 https://t.co/DMjVyjR9V7view source ↗
-
• twitter 1w neutralReal poverty is trading your time for money, then spending that money on things that can’t give your time back. Real poverty is trading your time for money, then spending that money on things that can’t give your time back.view source ↗
-
• twitter 1w neutral20 startups hiring right now (many fully remote) 1. @SpaceXAI: global 2. @NotionHQ: global 3. @Replit: global 4. @flytbase: Pune, India 5. @neatlogs: remote 6. @Nooqbook: remote 7. @saasflashstudio: remote 8. @DataUAcademy: Southeast Asia + global 9. @fal: SF / remote 10. @firecrawl: SF / remote 11. @turbopuffer: remo… 20 startups hiring right now (many fully remote) 1. @SpaceXAI: global 2. @NotionHQ: global 3. @Replit: global 4. @flytbase: Pune, India 5. @neatlogs: remote 6. @Nooqbook: remote 7. @saasflashstudio: remote 8. @DataUAcademy: Southeast Asia + global 9. @fal: SF / remote 10. @firecrawl: SF / remote 11. @turbopuffer: remote, NYC, SF 12. @attio: SF, NYC, London + remote 13. @Linear: North America + EU remote 14. @PostHog: North America + EMEA 15. @artie_labs: SF + remote 16. @gumloop: SF + Vancouver 17. @convex: SF 18. @zenml_io: SF 19. @SnorkelAI: SF + NYC 20. @nexcade_ai: London No referral needed. Go to their careers page and apply. Bookmark this + tag someone job hunting.view source ↗
-
• twitter 1w negative你是对的，orca 的桌面客户端与远程连接的交互有致命的缺陷、bug 不支持在输入框粘贴任何东西，也不支持上传图片（但是手机端都支持） 另一个会话发送的内容窜到当前对话里面被自动追加发送，这是最不能忍的， 还有各种莫名其妙渲染 bug 就不说了，这种还能忍一下， 今天试试 Paseo 和 t3 你是对的，orca 的桌面客户端与远程连接的交互有致命的缺陷、bug 不支持在输入框粘贴任何东西，也不支持上传图片（但是手机端都支持） 另一个会话发送的内容窜到当前对话里面被自动追加发送，这是最不能忍的， 还有各种莫名其妙渲染 bug 就不说了，这种还能忍一下， 今天试试 Paseo 和 t3view source ↗
-
• twitter 1w positiveWon first at the @supabase Select 2026 hackathon today with my project Fizz, a physical layer for agents! A huge thank you to @kiwicopple and @AntWilson and all of the amazing sponsors for making this a memorable event! Check out my project at: https://t.co/A6l71JzdOU (now in Waitlist!) Won first at the @supabase Select 2026 hackathon today with my project Fizz, a physical layer for agents! A huge thank you to @kiwicopple and @AntWilson and all of the amazing sponsors for making this a memorable event! Check out my project at: https://t.co/A6l71JzdOU (now in Waitlist!)view source ↗
-
• twitter 1w positiveOpus 5.5 on Max effort (Sound On): "A 24-second AI In Public motion reel in Remotion at 1920×1080, 60fps. Use our blue # 3D40FE, white, navy, and ice palette with the AI In Public logo and sparkle. Keep it fast, premium, and smooth with motion blur, glow, camera hits, HUD details, seamless transitions, kinetic type, t… Opus 5.5 on Max effort (Sound On): "A 24-second AI In Public motion reel in Remotion at 1920×1080, 60fps. Use our blue # 3D40FE, white, navy, and ice palette with the AI In Public logo and sparkle. Keep it fast, premium, and smooth with motion blur, glow, camera hits, HUD details, seamless transitions, kinetic type, terminal UI, neural visuals, particles, and a cinematic logo finale. Generate all suspenseful music and sound effects in code and sync every hit perfectly. End with “AI IN PUBLIC, learning AI, out loud.” Every frame and sound should be written in code." full prompt on here: https://t.co/Hp3qoiIww0 then read the full guide below: ↓view source ↗
-
• twitter 1w neutralWhen German engineers design an LLM : https://t.co/XT5xvdZYCN When German engineers design an LLM : https://t.co/XT5xvdZYCNview source ↗
-
• twitter 1w neutralIs it still "absurd" to claim that Tucker Carlson's "views are somehow completely anathema to conservatism" or "that he has no place in the conservative movement"? If so, please explain why. Is it still "absurd" to claim that Tucker Carlson's "views are somehow completely anathema to conservatism" or "that he has no place in the conservative movement"? If so, please explain why.view source ↗
-
• twitter 1w neutralat french restaurants, waiters are part of the kitchen staff, so they really know the food at french restaurants, waiters are part of the kitchen staff, so they really know the foodview source ↗
-
• twitter 1w neutralAs a software engineer of 18 years, I'm telling you now. Diversify your income. As a software engineer of 18 years, I'm telling you now. Diversify your income.view source ↗
-
• twitter 1w neutralThis is such a powerful lesson!! https://t.co/bjuVhnmsh4 This is such a powerful lesson!! https://t.co/bjuVhnmsh4view source ↗
-
• twitter 1w neutralGuess where I am (there’s a hint in this image) https://t.co/PvWarWrSRC Guess where I am (there’s a hint in this image) https://t.co/PvWarWrSRCview source ↗
-
• twitter 1w neutral🚨 Dashcam footage captures a serious accident near Chakrata. The incident reportedly occurred near Chilhaad village on Chakrata Road, when a car lost control and plunged into a deep gorge. ⚠️ The footage is a stark reminder of how unpredictable mountain roads can be. The video is reportedly from Friday. 🚨 Dashcam footage captures a serious accident near Chakrata. The incident reportedly occurred near Chilhaad village on Chakrata Road, when a car lost control and plunged into a deep gorge. ⚠️ The footage is a stark reminder of how unpredictable mountain roads can be. The video is reportedly from Friday.view source ↗
-
• twitter 1w neutralRT @NousResearch: Very surreal to see @linusgsebastian discussing his Hermes setup experience on their latest podcast (and pronouncing it c… RT @NousResearch: Very surreal to see @linusgsebastian discussing his Hermes setup experience on their latest podcast (and pronouncing it c…view source ↗
-
• twitter 1w positiveCLAUDE CODE CAN NOW TURN HIGGSFIELD INTO A ONE-PERSON AI VIDEO STUDIO. install this 19 skills, connect Claude Code to Higgsfield, then tell Claude what you want to create. run /ugc-hot-girl and let it create the character, generate the visuals, and produce the Seedance video for you. Claude controls Higgsfield throu… CLAUDE CODE CAN NOW TURN HIGGSFIELD INTO A ONE-PERSON AI VIDEO STUDIO. install this 19 skills, connect Claude Code to Higgsfield, then tell Claude what you want to create. run /ugc-hot-girl and let it create the character, generate the visuals, and produce the Seedance video for you. Claude controls Higgsfield through Playwright. you just review the output and make changes when needed. this is useful if you want to make UGC ads for brands without spending hours doing everything manually. you could even turn the workflow into a service and sell the finished content. if you’re building toward the solo creator income path, save this. repo below 👇view source ↗
-
• twitter 1w neutralhttps://t.co/TSlGTZcbsO https://t.co/TSlGTZcbsOview source ↗
-
• twitter 1w neutralHe jumped because he was asked to pay 3 Crores in Alimony and he didn't had the money Last message to father was - "You don't have to worry about arranging the money anymore" https://t.co/DwMdKGUHKN He jumped because he was asked to pay 3 Crores in Alimony and he didn't had the money Last message to father was - "You don't have to worry about arranging the money anymore" https://t.co/DwMdKGUHKNview source ↗