vizchitra on S Anand

The Curator's Dilemma - VizChitra 2026

Sat, 11 Jul 2026 11:56:37 +0530

Last week at VizChitra, I ran a “Dialogue” session. A new format for me.
I usually speak 80% in my workshops.
In this dialog, I spoke 20%.
The group discussed.

PART A
I showed 6 charts and said, “Pick the best.”
Then I shared the audience & purpose and asked:
“For THIS audience and purpose, will you publish, fix, or kill it?”
INSIGHT: almost no one said, “Ship”. That’s good – these were all drafts.

I also asked, “How will you verify it?”
No one knew.

PART B
I rotated the groups and asked them to critique the other groups’ critique.
That’s when I learnt that even internally, groups were divided.
It didn’t come out when they could only share ONE verdict.
It DID come out when discussing across two groups.
That was my biggest surprise - AHA moment.
Independent verification matters!

I asked them to share their final verdict:
“Which chart will you put your name against?”

The top-voted chart chart was 100% AI generated.
It was, also, something the Times of India literally published.

My takeaways:

We don’t really know how to verify charts.
We don’t agree on whether a given chart fits a given purpose.
We don’t often see disagreement, especially since we often ask for ONE opinion.

Full story: https://sanand0.github.io/talks/2026-07-04-vizchitra-dialog-curators-dilemma/

PS: This post is 100% human generated. I mean, I wrote every word, without even consulting an LLM. Pangram declared it 100% human-generated. Still, I can’t shake that feeling… that it smells AI-generated. Does this have a name?

Arvind Satyanarayan talk at VizChitra 2026

Wed, 24 Jun 2026 09:29:20 +0800

On Sat 4 July at Bangalore, Arvind Satyanarayan is speaking at VizChitra 2026 - a talk I’m keenly looking forward to.

I’ve been following Arvind’s work since Vega-Lite. It’s a grammar of graphics - something that makes data visualizations (charts) more structured. I tried switching to it our default at Gramener - but most felt it was too much to learn (they already knew Excel/Power BI) or too limiting (D3 can do more).

With AI coding agents, the learning is less relevant - AI will write the code. So, do grammars have less relevance? Arvind’s talk is about how they might actually be more important - maybe like a structured way to prompt.

Quite looking forward to this. Do attend if you’re interested in the cutting edge of AI-driven chart generation.

Here are some questions I hope to ask Arvind:

When someone hits the limit of a visualization grammar, but they know exactly what they want, what “escape” or extension mechanisms have you found most intuitive and useful?
With GoFish, you re-built a grammar rather than updating one. Why? I mean, what smells or gaps in existing grammars made you decide that way?
When YOU find a grammar limiting you, what tool(s) do you turn to today - and how do you work with them?

Submitting an AI-ded VizChitra Proposal

Sun, 15 Feb 2026 10:49:04 +0800

10:20 am. After submitting my VizChitra 2026 talk proposal, did a quick analysis of the submissions.

Copy the HTML from the submissions page and paste into Gemini.
Ask it: “Given this HTML, share a JS snippet I can copy and paste into DevTools that will return an array of objects containing all the useful information about each submission.”
Paste the JS snippet into DevTools and get the structured result.

Here’s the breakdown of submissions (excluding exchibitions):

	Community	Craft	Work	Tools
Talks	10	9	8	3
Workshop	4	2	1	3
Dialogues	1	0	1	1

There’s only one whitespace: a Dialogue for “Visualizations as Craft”.

10:40 am. Obviously, I have to submit my next proposal. Partly out of fear that my other proposal will be rejected in a the crowded “Visualizations as Craft” category, and partly to see if I can write a cool blog post about “How I used AI to maximize submission acceptance”.

So, I tasked Gemini 3 Pro, Claude Opus 4.6 - Extended Thinking, and ChatGPT 5.2 Extended Thinking - Web Search:

I want to submit a VizChitra 2026 proposal for a Dialogue in the “Visualizations as Craft”.

Here are the CFP details and other dialogue proposals for your reference

Research online for about the latest trends in AI in the craft of visualization and propose 10 topics for a Dialogue in the “Visualizations as Craft” category. Finally rank order these topics along with reason why this would be most useful for the community.

Then, rather than read it, I asked each other:

Here are the suggestions from other AI agents. Think about their opinion, factor in points that are better than what you suggested, drop what’s not as good, and recommend the top 3 topics. Also mention who had the best topics among you and the other two AI agents and why.

ChatGPT and Gemini said Claude had the best ideas. Claude said Gemini.

“The Curator’s Dilemma” bubbled up as the top idea. Then I asked each:

Which agent’s writing style (you vs the other two) would be best to frame a winning proposal for “The Curator’s Dilemma”?

Gemini and ChatGPT voted for themselves. Claude said none of these - write your own. The

Claude: Structured, thorough, and thoughtful with a poetic sensibility, but can come across as impersonal or overly soft — more like a well-organized conference paper than a passionate human voice.
Gemini: Punchy, direct, and provocatively sharp with a pragmatic edge, but can lean too declarative and confident, leaving little room for open-ended exploration.
ChatGPT: Highly analytical and structured with reviewer-friendly specificity, but tends toward a generic, corporate tone that lacks warmth, humor, and creative soul.

Anyway, I picked Claude and told it:

OK, write the proposal in for it, for now in your voice, and then I’ll rewrite it in my voice.

11:10 am. I converted the text to ASCII to prevent obvious AI detection like em-dashes, and started editing it the way I’d write it (the content was really good, actually, so editing was easy)

11:30 am. Finished editing. I was pleasantly surprised to find my co-founder Ganes Kesari’s Sloan Review article on “The Enduring Power of Data Storytelling in the Generative AI Era” as a reference. I might even have added a sentence or two to it. Small world!

It was also impressive how little I had to edit. It think it’s because:

This is a really good topic that resonates with me. I really have this problem and want to learn about it.
It clearly knew how to run a workshop better than I did. E.g. I would have picked 20 visualizations for the participants to review. But it knew we’d run out of time.
It writes really well. More verbose than me, but I found it hard to edit out the emotional punch I got from the phrases.

Anyway, the proposal will be on the submissions page soon. It takes a little over an hour to come up with a good proposal if you know the topic well.

So: experts in any field - you have less excuses not to submit more proposals. (Deep research prompt: As an expert in [TOPIC], suggest where I could submit proposals for talks.)

Can AI discover new data visualizations?

Sat, 14 Feb 2026 15:15:52 +0800

Here’s my talk proposal for VizChitra 2026:

Description

There’s stuff I know AI can do.

Create data visualizations. I just tell it to convert a dataset into a treemap, and it does.
Hallucinate. That’s a fancy word for “make stuff up”. I prefer calling it “creativity”.
Run forever. As long as I have token budget and can summarize the context, it can go on.

What if we combine these? What if we asked it to do research? If infinite monkeys will almost surely produce Shakespeare, how long will it take for the greatest AI to discover a truly novel data visualization that is useful?

This isn’t a talk. It’s an exhibition.

I’m not presenting. My AI monkeys are. They’ll show off what new data visualizations they’ve discovered, given the following constraints:

It’s novel. Check and make sure it’s stuff we haven’t seen before.
It’s useful. It has to reveal insights from data (even a niche kind).
It’s beautiful. Visually striking and engaging.

My role will just be a narrator of their work - since they can’t speak (or… um… )

Actually, my role is an admirer and critic - since they can’t critique themselves (but… actually… )

Well, I’m the person who paid for their tokens and will therefore take credit on stage. So there.

Video

Links:

About the speaker

Anand’s an LLM psychologist @ Straive. He prods AI to understand how it thinks. It prods back, teaching him how HE thinks. He’s ex-IITM, IIMB, INFY, LBS, IBM, BCG & other TLAs. He transcribed every Calvin & Hobbes strip over 7 years. AI does that now in 7 min.

Sun, 29 Jun 2025 10:25:14 +0000

We created data visualizations just using LLMs at my VizChitra workshop yesterday.

Titled Prompt to Plot, it covered:

Finding a dataset
Ideating what to do with it
Analyzing the data
Visualizing the data
Publishing it on GitHub

… using only LLM tools like #ChatGPT, #Claude, #Jules, #Codex, etc. with zero manual coding, analysis, or story writing.

Here’re 6 stories completed during the 3-hour workshop:

Spotify Data Stories: https://rishabhmakes.github.io/llm-dataviz/
The Price of Perfection: https://coffee-reviews.prayashm.com/
The Anatomy of Unrest: https://story-b0f1c.web.app/
The Page Turner’s Paradox: https://devanshikat.github.io/BooksVis/
Do Readers Love Long Books? https://nchandrasekharr.github.io/booksviz/
Books Viz: https://rasagy.in/books-viz/

The material is online. Try it!

Slides: https://sanand0.github.io/talks/2025-06-28-prompt-to-plot/

Sun, 29 Jun 2025 04:20:23 +0000

My VizChitra talk on Data Design by Dialog was on LLMs helping in every stage of data storytelling.

Main takeaways:

After open data, LLMs may the single biggest act of data democratization. https://youtu.be/hPH5_ulHtno?t=01m24s
LLMs can help in every step of the (data) value chain. https://youtu.be/hPH5_ulHtno?t=00m47s
LLMs are bad with numbers. Have them write code instead. https://youtu.be/hPH5_ulHtno?t=06m33s
Don’t confuse it. Just ask it again. https://youtu.be/hPH5_ulHtno?t=05m30s
If it doesn’t work, throw it away and redo it. https://youtu.be/hPH5_ulHtno?t=20m02s
Keep an impossibility list. Revisit it whenever a new model drops. https://youtu.be/hPH5_ulHtno?t=20m02s
Never ask for just one output from an LLM. Ask for a dozen. https://youtu.be/hPH5_ulHtno?t=22m20s
Our imagination is the limit. https://youtu.be/hPH5_ulHtno?t=26m35s
Two years ago, they were like grade 8 students. Today, a postgraduate. https://youtu.be/hPH5_ulHtno?t=00m47s
Do as little as possible. Just wait. Models will catch up. https://youtu.be/hPH5_ulHtno?t=31m45s

Funny bits:

This is how it’s done. How else would we do it? https://youtu.be/hPH5_ulHtno?t=04m31s
Some people call biases domain expertise. https://youtu.be/hPH5_ulHtno?t=22m50s
I don’t like work. I like playing Bubbles. So, have it do the work. https://youtu.be/hPH5_ulHtno?t=23m08s
More metrics, more quirky! https://youtu.be/hPH5_ulHtno?t=26m20s
Amuse me! https://youtu.be/hPH5_ulHtno?t=21m37s

Sat, 17 May 2025 07:11:21 +0000

This talk is an experiment. I am going to talk (literally) to ChatGPT on stage and have it do every kind of data analysis and visual storytelling I have ever done.

Bangalore. 27 June.

Of course, this is an LLM era away. So no promises. We might be doing something completely different on stage.