PhD @Cornell. Past: @MSFTResearch, @GoogleDeepMind, @ashokauniv. Sports fan!
Joined February 2013
- Tweets266
- Following219
- Followers778
- Likes2.7K
Pinned Tweet
Grad school applications are stressful! I shared *practical* tips from my experience at Microsoft Research last year and my slides were greatly appreciated. To encourage inclusivity in academia, I am making my slides public: agdhruv.github.io/files/prac…
#AcademicChatter @ThePhDPlace
Even technically strong papers are losing their appeal due to AI writing.
As a reader, it's fine: I can just have AI decipher the meaning. But as a *reviewer*, it's harder. Idk how to explain it... what the authors want to say seems to be hidden behind a wall of alphabet soup 😖
posts that didn't age well
#ARGCPV
My @WisprFlow usage has dropped drastically. I mostly used it to prompt my agents but dictation was making me lazy... I started writing sloppy prompts, leading to worse outputs. Turns out the intelligence per token of *my* thoughts is much higher when I'm forced to type them out
I interviewed at @SakanaAILabs (research intern) earlier this year and it was one of my favorite interview experiences in ~a decade. The technical assessment was so thoughtfully crafted and so much fun (like those psets in college that gave you eureka moments)! Every interviewer engaged deeply with my solutions from a position of curiosity and collaboration. Unfortunately I couldn't accept the offer due to visa constraints, but I highly recommend anyone interested to apply—I can vouch for the interview process, and it seems like an amazing place to work on fresh, interesting ideas in AI!
PSA: If you're applying for a research position at @SakanaAILabs (intern/full-time), we have a guide on what we look for
Researchers here pursue different directions - and may disagree - but have thought deeply about why
Over-reliance on LLMs to do your thinking isn't good
The NeurIPS hallucinated citations debacle is a good example of Goodhart's law:
When a measure (NeurIPS acceptance) becomes a target (prestige), it ceases to be a good measure (people will do anything to achieve it)
Okay so, we just found that over 50 papers published at @Neurips 2025 have AI hallucinations
I don't think people realize how bad the slop is right now
It's not just that researchers from @GoogleDeepMind, @Meta, @MIT, @Cambridge_Uni are using AI - they allowed LLMs to generate hallucinations in their papers and didn't notice at all.
It's insane that these made it through peer review👇
An Ode to Coding Before AI
Like most others, I learned to code in 2014, long before AI coding agents, autocomplete, and such. My friend and I would exchange HTML/CSS/JS tutorials on 1TB hard drives. I’d flip between VLC, Sublime Text, and Chrome on my family’s old HP laptop, trying to center a div or fix a PHP bug I barely understood. We built websites at high school tech competitions without any internet access. In college, I built a lowkey viral Facebook Messenger chatbot that shared our campus food menu and bus timings. It crashed when someone sent it a cat GIF haha. I "vibe-coded" so many other projects (the vibe came from my inexperience) and encountered creative bugs on the way.
Every bug was painful, but every bug taught me something: OS quirks, file systems, logs, APIs, threading, the GIL, tensor dimensions. These days, I use Cursor, Claude Code, and all the AI tools. They’re amazing! But I do feel a weird nostalgia. When AI writes so much of the code, you enjoy the product more than the process. As an engineer, I was wired to enjoy the process, but that's changing.
AI coding makes me productive, but a part of me misses when coding was slow, messy, and deeply personal...
I also wrote a longer version of this essay in case you're interested :)
medium.com/@agdhruv/an-ode-t…
Excited to be at the Alignment Workshop at @NeurIPSConf 2025 to talk about AI safety and alignment. Unexpectedly some of the conversations were about pre-training, not just post-training! Looks like Gemini 3 Pro is making pre-training cool again!!!
I've been thinking about AI applications beyond chatbots and coding agents. Here's one we came up with:
AI-generated sports commentary! Check it out:
AI commentary unlocks new possibilities
- Personalized commentary: beginner-friendly, numbers-focused, drama-heavy, biased to your team...your choice!
- Interactive: e.g. discuss strategy with the commentator as the game unfolds
- Democratizing sports: commentary can drive viewership for smaller/local games
Built this with @justachetan and Sushrut
My hot take on AI browsers: if it's Chromium-based (@perplexity_ai @OpenAI), I'll try it and move back to Chrome. Too much cognitive investment to leave behind (and Chrome will ship the same features anyway). The only way to dethrone Chrome is to rethink browsing – from scratch!
If you code in python and aren't using uv yet, this is your sign to jump ship! It's so fast and fun...I look forward to installing dependencies now lol
@astral_sh
Dhruv Agarwal retweeted
This @acm_chi paper finds that AI assistance homogenized writing in a controlled experiment with American and Indian participants (n=118). With a classifier, it was harder to predict writer origin without AI (83.5% vs. 90.6%).
dl.acm.org/doi/abs/10.1145/3…
🚀 Introducing MiniAI - AI made ridiculously simple!
Sick of OpenAI boilerplate? Tired of writing complex chains to do simple AI tasks? MiniAI is a minimal, flexible solution for byte-sized AI tasks.
pip install miniai
Examples ⬇️
9. 🎉Minimize boilerplate setup. Maximize productivity and rapidly build stuff!
📦 pip install miniai
🔗 github.com/agdhruv/miniai
Feel free to request more features and contribute!
("vibe-coded" this with @cursor_ai over the weekend haha; thanks to @karpathy for the motivation!)