Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Yohei Profile picture
@yoheinakajima
Jan 18, 2023 • 23 tweets • 11 min read • Read on X
It's been a blast building on #gpt3 since August. 😆

I've built and shared a few dozen apps and prototypes.

I often get asked this, so...

Here's a list of some favorites! 👇
1) ⚡️Official @OpenAI x @zapier integration

This is the most popular by far.

Originally an unofficial integration I built for myself, it is now powering the next generation of #AI x #NoCode tools.

2) 🔀Fuzzy Compiler

Turns "fuzzy/sloppy" code into clean code.

It speeds up my build a ton. It's mobile optimizes so I can generate code and add to Replit mobile app while I'm bouncing our baby down in the Ergo.

3) 🔕Error Analyzer

Analyzes error codes and spits out analysis + fixed code.

I don't use this as often, but helpful in debugging if my Fuzzy Compiler code doesn't work right.

4) 🕳️Mini Yohei - Founder Portal

This is a series of AI services for our portfolio companies in our founder portal.

Excited to add lots more!

5) 📄Deck Parser

Scrapes a PDF deck and extracts structured data.

Works on startup decks and VC decks.

6) 📰Due Diligence Support Tool

Identifies key risks based on a startup description.

This September version has improved a lot since, and...

7) ✍️AI Memo Drafting Tool

I combined the deck parser + DD support tool + more to build this.

This tool can draft an AI investment memo from a URL, description, or deck.
8) 📩School Email Summarizer

I made a personal web app that shows me summaries of all emails from my kid's school.
9) 📨emails.wtf

Then, I built a generic version of this.

If you email any email address: eg. x@emails.wtf, you will get a summary emailed back to you.

Access all summaries from a web app.
10) 🪄Magical To-Do List App

Built a folder in @todoist where I can add emails I need to send, and the AI drafts an email in gmail for me.

11) 🛠️Geppetto.me

I built a #nocode AI tool with #nocode.

Built on @softr_io, Geppetto allows you to quickly prototype #gpt3 based apps.

A lot of the apps you see above were initially prototypes with this.

12) 💬Mini Yohei Chat Bots

I've built 4 chatbot prototypes for founders.

- Pitch Mode: collects data
- Mentor Mode: helps founders with questions
- Guidance Mode: guides founders through a workshop
- Mean Mode: gives mean feedback

Mentor Mode:
13) 💕Healing Poetry

Stressed?

This app will write a beautiful poem to cheer you about about whatever is stressing you out.

Zero data stored, go try it!
14) 📢GTM Strategies

Identifies 7 specific go-to-market strategies based on a startup description. Was used 500 times in the first ~24 hours.

15) 🗞️Daily Tech News

Set up a Zap that scraped Techmeme and send me a summary every day.

I read this most mornings :)

16) 👍Sentiment Analysis of ProductHunt

Added capability into our memo drafting tool to scrape ProductHunt and generate a sentiment analysis report.

17) 🧑‍💻LinkedIn Bio Generator

Similarly, this scraped a person's LinkedIn and generates a bio.

18) 📲GPT-3 Siri on iPhone

Published a template for "talking" to #gpt3 via Apple Shortcuts:

Relevant (but separate), this one is for Stable Diffusion:

My 3 yr old can use these :)
19) 🌀Latent Blog/Search

A fun experience on what a parallel internet might look like.

This blog and search engine are fake. They make everything up as you click through.

Latent Blog:

Latent Search:
20) 🖼️Startup Graphics Generator

Not #gp3, but it's @OpenAI so let's count it.

This tool generates 100 startup friendly graphics of varying styles from a simple prompt.

21) ❓Q&A with Airtable without embeddings

While I love semantic search, it's not always the best solution.

This @airtable extension is fed the schema of the whole Airtable and identifies the table and column to search based on any query.

There's a lot more where this came from!

Check them here: yohei.me (my build-in-public log)

I'll probably keep adding to this thread, because I'm clearly going to keep building 😁

• • •

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

Yohei Profile picture
May 2
here friends, i open-sourced it: prettygraph



at 201 lines of code (69 in back, 132 in front), it's just a quick hack i did for myself to test this UIgithub.com/yoheinakajima/…
if you're interested in a web app, you can try out (which doesn't have highlights, but has more robust knowledge graph building).

the repo for instagraph is here: instagraph.ai
github.com/yoheinakajima/…
instagraph let's you combine graphs manually but if you're interested in automatically merging graphs, check out my more recent project: mindgraph

github.com/yoheinakajima/…
Read 5 tweets
Yohei Profile picture
May 1
look at this pretty little text-to-knowledge graph ui Image
Image
no confusion here Image
Read 7 tweets
Yohei Profile picture
Apr 19
great to see everyone at AI rabbithole event today!

as promised, here's my deck with abbreviated narrative.

(video was recorded, will share when available) Image
agents agents agents!

40+ agent related github projects today with 500+ stars, 90% of which are less than a year old. Image
where are we going? robots and virtual agents.

biggest difference is that robots are constrained in physical space, and virtual agents can run tasks in parallel and be in multiple "places" Image
Read 30 tweets
Yohei Profile picture
Apr 9
fascinating! the left and right images are built with the same agent log data (last 100 logs).

- left: each log is a unique node
- right: bundled edges/nodes by the function type of the log

result on right let's me easily see most used paths and functions.
Image
Image
Refactored the code and you can visually see the changes by comparing the two graphs!
Image
Image
made it so i can click on a function and see the recent log details of that specific function Image
Read 5 tweets
Yohei Profile picture
Apr 7
version 1 of auto-generate graph of actions taken by the agent

system_chat_handler_advanced is our chat interface endpoint, which used load_skill_description to find and pick the find_similar_files skill to find a relevant skills, which used the generate_embeddings skill to embed the input. then used generate_text_completion to generate the responseImage
filtered out the common functions used by the front-end so it shows me the logs that are most relevant to check Image
ooh breadthfirst makes more sense here Image
Read 8 tweets
Yohei Profile picture
Apr 4
Been talking lots about knowledge graphs and LLMs, specifically for autonomous agents, recently.

Organized some thought here if you want to dig in 👇

KG 🤝 LLM

🧵 (a thread)
For those not familiar, knowledge graphs are a type of data representation in the form of nodes (objects) and edges (relationships) and looks like this. Image
This structure allows for unique querying of relationship related data such as finding shortest path between two nodes, or further more complex reasoning. Image
Read 13 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!

Send Email!

:(