@jerryjliu0@jerryjliu0 Can you please extend your take?
My point is that chunking impact directly to the embedding semantic meaning that directly impact the retrieval performance.
RAG/retrieval might not be dead.
But chunking is dead.
There is no point overthinking your chunk size if the agent can dynamically expand context around a file.
Just leaked 110+ plug-and-play n8n templates that multiple industries are paying me $10K+ for.
Your weekend project: Pick any industry, copy-paste a workflow, start printing money.
The vault includes:
- Real estate lead machines (sold to 2 companies)
- Automotive inventory bots
- YouTube-to-TikTok content farms
- E-commerce customer journey automations
- SDR agents that close without you
- Healthcare patient follow-ups
- Legal document processors
- Social media engagement bots
From study agents (because fuck school) to manufacturing systems - every industry that prints money is covered.
The difference: These aren't broken templates with outdated nodes. They're battle-tested, profitable, and actually work in 2025.
Half sold for serious cash. Half are experiments that became goldmines. All are ready to deploy.
Follow, RT + Comment "vault" and I'll drop the entire collection before my accountant kills me for giving away the farm.
(Sorry to every consultant charging $10K for basic automations)
I used this n8n workflow to scrape X for top-performing posts in my niche (it's a big part of how I went from 600 → 6k followers in 13 days)
most creators scroll for hours to find content ideas that work...
whereas I just run this flow and get a full swipe file in minutes - organized by likes, comments, shares and URLs.
here’s what it does:
- drop in a keyword
- scrapes X for top posts
- pulls engagement data + content
- auto-sorts it all into a Google Sheet
now you've got data-backed insights ready to plug into your tweets, ads, or even video scripts.
workflow takes 5 minutes to set up
want the full JSON?
comment “SWIPE”, follow, + repost and I’ll send it over (must be following so I can DM)
the best way to find ad ideas, is to scroll TikTok, but nobody wants to do that for hours on end...
so I built an AI agent that can do it for you, completely hands-off
just give it a keyword and it:
– scrapes the top-performing TikToks
– pulls the pain points, trigger events, and emotional hooks
– rewrites the viral script for my product or service
want the full n8n flow + set up guide?
like + comment “script” and I’ll send it over (must be following so I can DM)
Just created a 30+ page doc breaking down n8n & building automation workflows.
Just follow + comment "n8n" & I will DM you the pdf.
This is completely FREE. Don't even want your email.
A simple follow will do :)
I compiled 200+ n8n automation templates you can copy & paste into your business or sell to other companies.
Just straight plug-and-play systems for:
– Lead gen
-Content creation
– Email outreach
– CRM updates
– AI workflows
– Slack/Discord bots
…and more.
Follow + Reply “n8n” and I’ll send it over.
This is completely FREE. Don't even want your email.
Specifying cameras and lenses in your Midjourney prompts really doesn't do anything.
Instead, use film stocks. They're really powerful, especially when paired with an era.
Here are 8 unique film stocks plus a short tutorial on multi-prompting to give your styles a boost.
ChatGPT is free.
But it's a matter of how well you use it.
That's why I made this free document for you:
• 25+ ChatGPT prompts
• 60+ AI and dev tools
• 35+ Low/No code
To get it,
• Like
• Reply "👋"
• Follow me (so that I can DM)
Instead of just getting answers with #ChatGPT, start having it take action ⚡
Here is how we created an enhanced version of ChatGPT that is connected to the internet, our @SlackHQ and @NotionHQ. Powered by @langchain
Agipt helps generate and save any task we need.
I am joining the Electrical & Computer Engineering Dept of The University of Texas - Dallas @UT_Dallas as an Assistant Professor this month. At UTD, my team will work on machine learning and inclusive speech synthesis. If you are interested in joining my team, do approach me!
Ojo a la GeForce RTX Serie 30 de @ZOTAC. #UltimatePlay
⚪ HoloBlack: acabado holográfico.
⚪ Cooling IceStorm 2.0
⚪ Iluminación ARGB SPECTRA 2.0
¿Quieres tener la oportunidad de ganar una?
Responde con un GIF mostrándonos el hype que tienes, comenta con #UltimatePlay
My first day as an Assistant Professor at Singapore University of Technology and Design (SUTD)! SUTD is established in a collaboration with MIT, in Singapore. I will mostly work on #speech and #MachineLearning. I'll still continue to be a researcher at NUS HLT. Very excited! 🌸
OK then, First Order Motion Model by Aliaksandr Siarohin et al. works perfectly. Here a talking Nefertiti for you.
"Observing frame pairs (source and driving), each extracted from the same video, it learns to encode motion."
aliaksandrsiarohin.github.io/first-order-mo…#ArtificialIntelligence
I'm starting to write the conclusion of the CNN chapter for our book, and want to suggest some other "patterns of connectivity" other than convolutions and fully connected. Anyone got interesting examples?
Only 9% of plastic bottles are ever recycled. The rest destroy our oceans.
For every RT in the next 24 hrs @DeloitteDigital will stop 1 plastic bottle from reaching our oceans 🌊
🔁 1 RT=1 bottle
Let’s unite behind #mylastplasticbottle and make a real impact.
#CannesLions