Preprint and blogpost coming soon
Preprint and blogpost coming soon
Paper accepted at MSR 2026 : "Investigating Autonomous Agent Contributions in the Wild." It was an absolute pleasure working with the extremely talented coauthors Razvan Mihai Popescu, David Gros, Andrei Boลฃocan, Maliheh Izadi , and Prem Thomas Devanbu.
My experience jerry-rigging a web app to build software on my phone. It's more feasible than you think. rahulpandita.me/blog/2026-01...
Weekend XC with my favorite passenger(s). The mini-mes were not impressed
Mine is half-baked, rotting in Overleaf and Google Docs!
What ChatGPT thinks I did this year
For very large values of Sometimes
Image from X
100 mph wind gusts
Image from X
TIL that adding a screenshot as an input to iterate with Copilot is not that widely known. I've been using it for a while to streamline/debug my UX code.
Image from X
Lately, I've been experimenting with agentic PR reviews. Here's the prompt I use. I'm curious what you folks use:
https://gist.github.com/rahulpandita/ebc337ca7a6c67823cdcca065d04fc4a
As agentic and human parallelism explode with exponential increasing in code output via LLMs , I think thatโs the next frontier we should be optimizing for in code models.
Image from X
Model builders, if you're taking recommendations, I would love to have a coding model that is really good at git rebase, merges, and resolving conflicts.
Karpathy's suggestion of using LLMs as a simulation machine "Who are the best people to answer XYZ and what would they say about it?" is a wonderful self-reflection heuristic.
Leverage it to the fullest before the next round of RLHF makes it ineffective for upcoming models. ๐ก
How the programming evolved from pressing ctrl+C and ctrl+V to clicking Allow
We are at a point were model capability is not a limiting factor human cognition is
testing http://ferryman.io
<3 Aviation Recap!
#ffRecap
https://plan.foreflight.com/recap/c6c14ff8-ce09-47a0-be09-3ee96bfedf79
via @ForeFlight
Not everyday you get to perform run-up in your tiny cessna next to a T-6 Texan
My latest post is out!
๐ Introduce "Semi-automatic Performance Engineering"
๐ A Grand Challenge for CS
๐งฉ Why it's hard, heterogeneous
โจ Show GitHub Agentic Workflows "Daily Perf Improver"
๐ฎ What's Possible, Potential, and Delusional
๐งน Let's tackle technical debt!
dsyme.net/2025/10/12/t...
Some thoughts on LLMs, Autopilot, and VibeCoding rahulpandita.me/blog/2025-10...
plane animation inspired by @wattenberger.com's wattenberger.com/thoughts/fis...
Degrees are merely proof of the money you've spent on a course. Education is knowing how to use what you learned.
rahulpandita.me/blog/2025-06...
There is high likelyhood of the Bidding wars in AI companies to converge on global maxima of Nelson Bighetti (aka Big Head).
awesome work by @kcieslak.io
Leadville (KLXV) North Americas highest elevation (9934โ) airport โ
Mt Elbert Coloradoโs tallest peak in the background!!
I'm now a FAA-certified private pilot(ASEL) and can joke that I'm a pilot working on
@githubnext.com #Copilot.
Like my dad, we will glitch in real-time to adjust our 9-channel knob mindset to a 999-channel remote, but I am confident that we can overcome it. And the sudden "1000-fold expansion of possible coding universe" is only going to increase the demand for programming(pun intended)...