Among all the cool things #ChatGPT can do, it is super capable of handling and manipulating data in bulk, making numerous data wrangling, scraping, and lookup tasks obsolete.
Let me show you a few cool tricks, no coding skills are required!
(A thread) 👇🧵
Let's start easy by heading to chat.openai.com/chat and pasting a list of 60 countries in the text field
Let's ask #ChatGPT to give us the main language, latitude, longitude, and country code for each of these countries
That was easy enough, right?
Now let's add more data to our output by asking #ChatGPT to provide the population of each of these countries
Uber cool! 😎
Let's ask ChatGPT to wrap these results in a table
Let's conclude this thread by asking #ChatGPT to create a @streamlit app with a CSV uploader and filter boxes to filter `longitude`, `latitude`, and `country code`.
Not only does #ChatGPT displays the code, but it also provides clear explanations for each step! 👏
This is just a quick overview of what you can do with #ChatGPT.
I'm only scratching the surface here.
For more cool things you can do with it, check out my other thread
1. Follow me @DataChaz to read more content like this. 2. Share it with an RT, so others can read it too! 🙌
Note that while #AI is capable of handling tasks such as sourcing and sorting, as well as some aspects of app development, it is not yet advanced enough to replace the need for human verification.
Even with its impressive capabilities, AI still requires human oversight.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
🚨 Karpathy’s new set-up is the ultimate self-improving second brain, and it takes zero manual editing 🤯
It acts as a living AI knowledge base that actually heals itself.
Let me break it down.
Instead of relying on complex RAG, the LLM pulls raw research directly into an @Obsidian Markdown wiki. It completely takes over:
✦ Index creation
✦ System linting
✦ Native Q&A routing
The core process is beautifully simple:
→ You dump raw sources into a folder
→ The LLM auto-compiles an indexed .md wiki
→ You ask complex questions
→ It generates outputs (Marp slides, matplotlib plots) and files them back in
The big-picture implication of this is just wild.
When agents maintain their own memory layer, they don’t need massive, expensive context limits.
They really just need two things:
→ Clean file organization
→ The ability to query their own indexes
Forget stuffing everything into one giant prompt.
This approach is way cheaper, highly scalable... and 100% inspectable!
Wow. Insanely fast turnaround from @himanshustwts!
A full breakdown of @karpathy’s self-improving wiki framework,
walking through every stage from ingestion to what comes next 👀
@himanshustwts @karpathy Omar took a v. similar approach with @Obsidian
THIS is the wildest open-source project I’ve seen this month.
We were all hyped about @karpathy's autoresearch project automating the experiment loop a few weeks ago.
(ICYMI → github.com/karpathy/autor…)
But a bunch of folks just took it ten steps further and automated the entire scientific method end-to-end.
It's called AutoResearchClaw, and it's fully open-source.
You pass it a single CLI command with a raw idea, and it completely takes over 🤯
The 23-stage loop they designed is insane:
✦ First, it handles the literature review.
- It searches arXiv and Semantic Scholar for real papers
- Cross-references them against DataCite and CrossRef.
- No fake papers make it through.
✦ Second, it runs the sandbox.
- It generates the code from scratch.
- If the code breaks, it self-heals.
- You don't have to step in.
✦ Finally, it writes the paper.
- It structures 5,000+ words into Introduction, Related Work, Method, and Experiments.
- Formats the math, generates the comparison charts,
- Then wraps the whole thing in official ICML or ICLR LaTeX templates.
You can set it to pause for human approval, or you can just pass the --auto-approve flag and walk away.
What it spits out at the end:
→ Full academic paper draft
→ Conference-grade .tex files
→ Verified, hallucination-free citations
→ All experiment scripts and sandbox results
This is what autonomous AI agents actually look like in 2026.