Yohei Profile picture
Mar 29, 2023 16 tweets 7 min read Read on X
🔥1/8
Introducing "🤖 Task-driven Autonomous Agent"

An agent that leverages @OpenAI's GPT-4, @pinecone vector search, and @LangChainAI framework to autonomously create and perform tasks based on an objective.

"Paper": yoheinakajima.com/task-driven-au…

[More 🔽] Image
🚀2/8 The system can complete tasks, generate new tasks based on results, and prioritize tasks in real-time. It demonstrates the potential of AI-powered language models to autonomously perform tasks within various constraints and contexts.
💡3/8 The autonomous agent uses GPT-4 for task completion, Pinecone for efficient search and storage of task-related data, and the LangChain framework to enhance decision-making processes. #GPT4 #Pinecone #LangChain
🎯4/8 The system maintains a task list for managing and prioritizing tasks. It autonomously creates new tasks based on completed results and reprioritizes the task list accordingly, showcasing the adaptability of AI-powered language models. Image
🔧5/8 To complete tasks, the system uses GPT-4 and LangChain's capabilities, enriching and storing results in Pinecone. This integrated approach allows the AI agent to interact with its environment and perform tasks efficiently.
🧠6/8 The system generates new tasks based on completed task results and prioritizes them using GPT-4. This allows the system to adapt and respond to new information and priorities.
🔮7/8 Future improvements include integrating a security/safety agent, task sequencing and parallel tasks, generating interim milestones, and incorporating real-time priority updates. Image
🤝8/8 This new approach paves the way for AI-powered language models to autonomously perform tasks within various constraints and contexts, enabling new applications and opportunities. Big thanks to all involved! #AIResearch #GPT4 #Pinecone #LangChain
📜 APPENDIX

🧵Thread (above) generated by GPT4 based on paper
📄Paper generated by GPT4 based on code
📊Graphs in paper generated by GPT4 based on code
💻Code generated by GPT4 based on prompt

*For each, many prompts to adjust initial output Image
Backstory 1/5:

Honestly, I was just trying to play around w the idea of an "AI founder" after seeing the awesome #HustleGPT movement.

That led to this prompt 2 days ago.

Backstory 2/5:

About 50 prompts later (dev docs, error codes, etc.), I shared this working prototype.

It's amazing that its first task is to create its next task - and it just keeps going.

Backstory 3/5:

Realized it could be provided any core objective, in this case "make the world a better place".

Pretty fascinating to watch but also scary.

Backstory 4/5:

Interestingly, when I asked it to generate as many paperclips as possible, it first generated security measures.

Which was then picked up by the creator of the Paperclips Apocalypse theory himself.

Led to lots of AI safety reading.
Backstory 5/5:

Sharing the original experiment led to many shared concerns and potential counter measures being shared publicly. Including awareness of what people are likely doing privately.

I believe this is a good thing.
Agh, my site has security issues.

So found the second best place to post it.

linkedin.com/pulse/task-dri…
And here you go!

Open-sourced a paired down version I’m cheekily calling “Baby AGI”.

Repo in thread:

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Yohei

Yohei Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @yoheinakajima

Mar 16
Open-sourcing "MindGraph", a proof of concept starter kit for building and querying against an ever-expanding knowledge graph with natural language!

- multiple input types
- simple interface
- basic search/RAG against knowledge graph
- easily extendable with integrations
- basic database swapping

GitHub in 🧵Image
Quick background is that I paused on BabyAGI work after the BabyFoxAGI mod because I felt I was missing some pieces.

Went deep on knowledge graphs (KGs) and released Instagraph () which lets you build, merge, and edit KGs....instagraph.ai
Oh, and before I keep going, here's the GitHub:

This is one of my bigger projects (multiple files) which I'm not used to, so be kind plz. Hopefully still some interesting and fun patterns in here for you.github.com/yoheinakajima/…
Read 6 tweets
Nov 26, 2023
Okay @tldraw is pretty addicting



1) draw your UI
2) use text to describe
3) highlight (i.e. draw box around), and
4) click the blue "make real" on top right) makereal.tldraw.com
super quick prototypes that don't actually work, but give you the sense of what it would feel like to play with? count me in!
No but seriously, I could do this all day.

I wonder how many OpenAI calls each one of these takes...
Read 5 tweets
Nov 7, 2023
The Assistants API is awesome, had to build something...

Open-sourcing "GPTvsGPT" 🕵️🕵️
(109 lines of code)

A simple template to have two AI Assistants converse. What's exciting is the ability to extend these with retrieval, data, and custom functions.

GH/Replit in thread 🔽 Image
As you saw above, you set the parameters for two Assistants, then feed that in with the topic, and number of messages you want.

You'll get something like this: Image
Here is the Github:

Here is the Replit:

As usual, this is only meant as a starting point to build something awesome. Lots of directions you can take this!

(img below courtesy of DALLE3 and dingboard) github.com/yoheinakajima/…
replit.com/@YoheiNakajima…
Image
Read 14 tweets
Sep 24, 2023
famous songs as knowledge graphs Image
Image
Image
Read 5 tweets
Sep 11, 2023
obsessed w this new learning tool
Image
Image
need some time before sharing the tool but in the meantime… any requests?
@provisionalidea Also these types of things show up pretty often still
Read 5 tweets
Sep 1, 2023
Introducing BabyFoxAGI 👶🦊🤖

Newest mod of @babyAGI_ with:

🔂 Self-improving task lists (FOXY method)
💬 Novel Chat UI w parallel tasks
🛠️ New skills (DALLE, Airtable, etc)
📄 It’s own README

Breakdown, Github, Replit 👇
BabyFoxAGI is mod of BabyElfAGI, in a series of mods w the naming of Baby<animal>AGI in alphabetical order:

🐝Bee, 🐱 Cat, 🦌 Deer, 🧝 Elf, 🦊 Fox

You can find the thread introducing BabyElfAGI here: x.com/yoheinakajima/…
🔂 Self-improving task lists (FOXY method)

By storing a final reflection at the end, and pulling the most relevant reflection to guide future runs, BabyAGI slowly generates better and better tasks lists.

Described more in this thread: x.com/yoheinakajima/…
Read 12 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(