yo wtf, Microsoft's newly released AutoGen is fk'in dope..

- allows for multiple agents that align to one goal
- human input allowed

🤖 I created 5 agents to help me plan a 30-day iternary in Bangkok

(results below ↓) 5 agents:

🥳 Fun Manager - maximizes fun
🎆 Executive Assistant - makes sure work gets done
💪 Gym Trainer - makes sure training gets done
✈️ Planner - Suggests plan
👄 Critic - Double check plan, claims, code from other agents and provide feedback

How I Negotiated Multiple 250k+ Software Engineer Offers

No course needed, I'll teach you for free

(Use these lessons to negotiate anything..) A bunch of people DM'd after my previous viral thread

So here it is. A quick guide on how to actually negotiate.

1-3 emails can be the difference between you adding 20-75k to your inital offer

Onwards.

https://twitter.com/pwang_szn/status/1674719490993688577

🪄 INTRODUCING: NotionWizard (Chat-to-Notion)

(Showcasing power of @OpenAI Functions)

1) Type in Prompt in @streamlit 💬
3) 📖 Get back url to new @NotionHQ page (w/ the help of OpenAI functions)

Demo, Code explained & Github Link↓ 👀 Live Demo:

How I Made $72,000+ Profit Slinging T-Shirts on the Side

Fun Facts:
- Started in the business in 2017 (my first business!)
- 6000+ uploaded t-shirt designs (I pay $.5 per design)
- <1% of the designs make 80% of the revenue
- $1000-$1500/month (pure profit)

🍿 The entire story: More proof of earnings:

In Jan 2022, I wasted 3 months no-life grinding @LeetCode and ended up with 3 decent offers (all software eng):

- $250k+ from @Uber
- $270k+ from @Affirm
- $260k+ from @gopuff

and then a bunch more 200k+ offers.

5 lessons i learned: before we start..

no, I don't I have a leetcode course to sell you, i'm cheap af and used YT to interview prep (you can too!)

why am i writing this? my ego is heavily tied to follower # on this bird app, so click that lil' follow button @pwang_szn

"How I 100% Automated Generating Subtitles for buildfastcourse.com module videos"

1. Setup a @zapier to trigger when new video is added
2. Setup automation in @Dropbox to convert .mp4 to .wav
3. Use @DeepgramAI to generate transcript, convert to .srt format on Django server Goal:

💬 Generate 95%+ accurate transcription for all the videos w/o paying some other service for overpriced human transcription that can cost >$1.5 per minute

Technical choice:
>> 🤖 Using Zapier bcuz I don't want to maintain webhooks on my server

"The Complete Bozos Guide to Document Loaders in @LangChainAI"

• Document Loader basics
• When to use Document Loader
• Import data from Text & CSV
• Loading data from Discord, Notion, Telegram

Save This ↓ What's the problem?

→ We want to pass our personal data when chatting with the LLM.

⭐ We need a way to load the data to our LLM. To do that, use Document Loaders.

"The Complete Bozos Guide to Fine-tuning"

• What is Fine-tuning?
• How to Fine-tune a custom LLM.
• When should we use fine-tuning?
• When NOT use use fine-tuning?

Save This ↓ Basic info on Fine-Tuning:

Retrievers in @LangChainAI are surprisingly powerful.

• Basic info on Retrievers
• Index vs Retriever
• When do you need a Retriever?
• Retriever examples

(All you need to know in under 6 tweets.)

Save This ↓ What is a Retriever:

Vector databases may be the next "big thing"

• Vector databases explained
• What is Unstructured data?
• When to use vector databases
• Embeddings.
• Use-cases

All you need to know in under 10 tweets.

Save This ↓ Why do we even need a database?

→ We have data that we want to store.

Relational databases (like Postgres) or No-SQL databases (AWS DynamoDB) can store structured data but there is one inherent problem.

→ Unstructured data is hard to store in relational databases.

✨ Here's all you need to know about Chains in @LangChainAI

(In less than 3 minutes of reading..)

• Basic Information about Chains
• LLM Chain Explained
• Sequential Chain
• Four types of Chains

Save This ↓ Basic Information about Chains:

"How to Create Your Own Personal Chatbot (without ripping your hair out)"

I've broken it down into bite-size chunks.

Save this ↓ Here's a high level of what we're doing:

Everything you need to know about Prompts in @LangChainAI :

• Basic Information
• Example Prompts
• Output Parser

Save This ↓ Basic Information

All you need to know about LLMs:

• Overview
• Using LLMs in @LangChainAI
• Using open-sourced LLMs
• Chat Model
• How do we embed text?

Save this ↓ LLMs explained:

Everyone's been asking for it.

Here it is. I've broken it down @LangChainAI Agents into bite-size chunks.

• Agents Basics
• Tools
• Agent Executor
• AutoGPT
• BabyAGI

Save this ↓ Agents explained:

Memory in @LangChainAI is a big deal.

It was a lot to go through, but I broke it into bite-size chunks.

• 4 Memory Types Explained
• How to use Memory in a Chain
• How to add Memory to an Agent

Save this ↓ ConversationBufferMemory:

• Memory allows for storing of messages
• Extracts the messages in a variable.

Pro: Basic to understand/pickup

INTRODUCING: JarvisBase, a Jarvis for your Knowledge Base.

1) 🤖Scrape & store data (Scraped @huggingface docs, stored in @activeloopai)
2) Ask question about the data w/ @LangChainAI & @streamlit
3) Gives an answer w/ audio voice-over. 🔊

Demo, Code explained and GitHub Link↓ Live Demo:

Indexes in @LangChainAI are confusing.

But I've broken it down into bite-size chunks.

• Basic Information
• Document Loaders
• Retrievers
• Vector Stores
• Text Splitters

Save this ↓ The basic information about Indexes 🧙

INTRODUCING: Story Storm, an A.I Storyteller 📚🌩️

1) 💡Type in prompt
2) Generates story w/ AI @OpenAI & @LangChainAI
3) Create audio voice-over w/ @elevenlabsio. 🔊
3) 🎨 Create story-cover w/ Stable Diffusion @replicatehq.

(<69 lines)

Demo, Code explained and GitHub Link ↓ 1/ Live demo: 🎤

(Peep the 30+ Langchain tabs open 💀 )

🥁 INTRODUCING: Drake Bling Bakery, an AI meme generator

1) 💬 Type in any topic
2) Generate custom Drake meme w/ AI with the help of: @imgflip, @OpenAI @streamlit 🎨

(The memes in the demo about @levelsio and @vercel are 🤣)

Demo, Code explained & Github Link↓ The entire code:

(It's not too bad, <72 lines of code)

🪄 INTRODUCING: Figma Chat Wizard

1) 🤖 Import design from @figma (with the help of @LangChainAI Loader)
2) Chat with the design in @streamlit 💬 and @OpenAI.
3) 🎨 Design and code is returned

Demo, Code explained & Github Link↓ 1/ Live Demo: