Akanksha Chatterjee

[Roberto Cerina @RobertoCerina]

A few months ago the great @AkankshaCh50293 put out a forecast for the West Bengal Election based on Silicon Samples that ended up being off -- it turns out, we found a bug in her code !

After fixing, our silicon sample *would have been* the least-wrong “poll”, correctly observing a massive swing in favour of the NDA.

She has updated her blog post below to describe the error, and show what happens after fixing. We look forward to re-applying our methodology to the upcoming state elections this coming year !

https://t.co/yq0jYMJBll

[Roberto Cerina @RobertoCerina]

Fortunately, there are plenty of elections in the world’s largest democracy coming up next year, including a very important one in India’s largest state of Uttar Pradesh -- @AkankshaCh50293 and I will be back with a more robust strategy for those ! Stay tuned ... 4/4

[Akanksha Chatterjee @AkankshaCh50293]

@AashaySachdeva here's the full article in case you want to have a read! https://t.co/tDtu9jEGtm

[aashay sachdeva @AashaySachdeva]

Sarvam-105B's prediction for West Bengal Election. Let's see how close this lands!

[Akanksha Chatterjee @AkankshaCh50293]

Excited to share that I will be presenting in @WCEurope 2026 in Krakow, Poland!

WordPress for scientists: building engineering websites at CERN https://t.co/FM8ptmVrNx

(this will also be the first conference I will attend)

[Roberto Cerina @RobertoCerina]

Will her forecast prove correct ? It’s difficult to tell, as this has never been attempted before and the ability of Sarvam to ‘reason’ like a WB voter is an open question.

Her effort presents a novel methodology for “silicon sampling" in difficult-to-poll parts of the world.

[Roberto Cerina @RobertoCerina]

‼️📢New Blog 🤖

Can an AI Poll Predict the Winner in the West Bengal Election ?

Absolutely phenomenal piece of work by my UvA CSSci student Akanksha, who uses LLMs to simulate the West Bengal electorate, mixing traditional survey science with SoTA AI:
https://t.co/SDSWKCnKlE