Lighthouse ꧁IP꧂

[Poonam Soni @CodeByPoonam]

Google just changed note taking forever.

NotebookLM got massive upgrades.

5 Powerful features you can't afford to miss:

[Abhishek @HeyAbhishek]

Grok 4 can help create McKinsey-style visuals.

No more spending hours formatting diagrams or building charts from scratch.

Here’s how to create stunning graphics in just few minutes:

[God of Prompt @godofprompt]

Grok 4 is dangerously good.

But 99% of people are sleeping on what it can actually do.

I’ve used it to build apps, generate content, automate deep research, and more.

Here are 10 ways to use Grok 4 that feel like cheating:

[Alex Prompter @alex_prompter]

AI just killed the marketing department.

You can now use Claude 4 for market research, content creation, writing viral ads, SEO optimization, and campaign planning.

Here’s the exact mega prompt we use to automate our entire marketing workflow:

[Alex Prompter @alex_prompter]

Claude 4 vs ChatGPT-4o vs Gemini-2.5

Which one writes good content?

I tested all 3 of them using multiple prompts.

And you won't believe which one became my writing partner.

Here are 5 ways I tested Claude, Gemini, and ChatGPT:

(Video demos are included 👇)

[Lighthouse ꧁IP꧂ @phohaidang]

@Trong0322 @maplefinance Còn RSS3 thì sao em? Còn cơ hội nào hco em ấy k?

[Lighthouse ꧁IP꧂ @phohaidang]

I'm loving $BDXN @bondexapp 🚀

[Bondex @bondexapp]

📣 Big News: Bondex has successfully raised over $10M in our latest investment round!  🥳 🎉
Our funding round was led by prominent VCs such as @animocabrands, @Morningstar_vc, and @CoinList. 💰
Alongside our incredible community, their support fuels our mission to further Web3 professional networking! 🌐✨

👉 Read full article via @TheBlock__ https://t.co/swfGDwT4a8

[Rory Flynn @Ror_Fly]

Google Veo3 T2V Prompting Guide.

For consistent iterations.

TIPS:
+ Start with a structure
+ Create a base prompt
+ Iterate small elements

BASE PROMPT STRUCTURE:
[PERSPECTIVE], [SHOT STYLE + DETAILS], [SUBJECT DETAILS + ENVIRONMENT], [SCENE DETAILS], [SOUND DESCRIPTION], [LIGHTING], [FILM STYLE]

(Evolution in thread)

#google #veo3 #promptshare

[Min Choi @minchoi]

Google Veo 3 realism just broke the Internet yesterday.

This is 100% AI

10 wild examples:

1. Street interview that never happened

[Nelly; @nrqa__]

10 insane ChatGPT prompts that are so useful they feel illegal to know:

(🚨 don’t say I didn’t warn you)

[Min Choi @minchoi]

It's only been 48 hours since Google dropped Gemini 2.5 Pro (I/O edition)

And people can't stop building with it.

10 wild examples + links:

1. Build Interactive app from a sketch

[Abhishek @HeyAbhishek]

10 AI Tools to replace your tedious work

Gamma AI —Create presentation with AI

Gemini Flash —AI image generation and editing

Perplexity AI —Web search/summarization

Replit agent —Build MVPs/mobile apps

Typefully —Social media management

Grok-3.5 —Deep research tasks

Windsurf AI —Best for AI coding

Kling AI —Create Stunning videos

ChatGPT —Brainstorming

Lovable —AI Websites

So, which is your favourite AI tool?

[Min Choi @minchoi]

Crazy week in AI🤯

- NVIDIA drops open sources Parakeet ASR
- Gemini 2.5 Pro (I/O edition) drop
- OpenAI buys Windsurf for $3B
- Cursor valued at $9B
And more...

10 wild news drops + how to make sense of them: 👇

[Upside GM 👋 @gm_upside]

🔎 07 chỉ số Warren Buffett để tìm hidden gem & Cách áp dụng trong crypto? 💎

1. Buffett Indicator
2. P/E
3. PEG Ratio
4. ROE
5. Free Cash Flow Yield
6. Giá trị nội tại
7. Biên an toàn
8. Áp dụng vào crypto

Tác giả: @jackvi810

Mong anh em ủng hộ @gm_upside một like & retweet nếu bài viết hữu ích 😍

[Nelly; @nrqa__]

STEAL THESE 10 PROMPTS TO RESEARCH AND WRITE FASTER THAN EVER:

try Alibaba Qwen-3 : https://t.co/HfwW0bKcWp

----
Get more info👇

[Umesh @umesh_ai]

So, ChatGPT imagines how a child might look based on the parents' photos?!

[AshutoshShrivastava @ai_for_success]

This prompt will make your ChatGPT go completely savage 😂

[Femke Plantinga @femke_plantinga]

Vector databases are the FUTURE of data storage and retrieval in AI.

But what do you know about them?

While everyone's talking about Agents, LLMs and GenAI, vector databases are quietly powering it all behind the scenes. 𝗛𝗲𝗿𝗲'𝘀 𝘆𝗼𝘂𝗿 𝗰𝗿𝗮𝘀𝗵 𝗰𝗼𝘂𝗿𝘀𝗲 𝗼𝗻 𝘁𝗵𝗲 𝟲 𝗰𝗼𝗿𝗲 𝗰𝗼𝗻𝗰𝗲𝗽𝘁𝘀:

Unstructured Data Objects →
These are your raw data: text, images, audio, or videos that don't fit neatly into traditional databases.

Vector Database →
The powerhouse that stores both your original data AND its vector representation in one place. It's like having a library where books are organized by their actual content similarity, not just alphabetically.

Vector Embeddings →
Think of these as your data's DNA code. They're arrays of numbers that represent your data in a way AI can understand.

Embedding Models →
These are the special AI models that create those vector embeddings. They've evolved from simple models like Word2Vec to sophisticated transformer models like BERT. They're like translators that convert your data into the language of vectors.

HNSW (Hierarchical Navigable Small World) →
This is the secret sauce that makes vector searches super fast. It creates multiple layers of connections between vectors, like an efficient highway system for your data. It's super scalable and allows you to balance between search speed and accuracy.

In short, vector databases:
• make searching through unstructured data efficient
• power semantic search in AI applications
• enable similarity-based recommendations
• enable RAG (Retrieval-Augmented Generation) and other modern AI applications

📌 Resources to save for later:
- A Gentle Introduction to Vector Databases: https://t.co/8s94u0CGyC
- What is a Vector Database? https://t.co/JtDnNMsn8a