krishna
bala.dev
krishna
@bala.dev
motion planning & robotics, working on AVs 🚙
November 5, 2026 at 8:13 PM
Reposted by krishna
Pouring a cup of coffee looks trivial. It isn’t. Humans effortlessly control nonlinear liquid dynamics across different vessels and speeds—while robots still struggle. In our new preprint, we ask how the human motor system solves this everyday control problem. 1/5
September 3, 2026 at 3:17 PM
Reposted by krishna
This is a robot failing to grasp a ball. Almost every robot lab produces clips like this daily… and almost all of them get thrown away. This is the most abundant but underused resource in robot learning. We’re collecting all of it now as “OopsieData”, please join us at oopsie-data.com! (1/13)
July 30, 2026 at 7:19 PM
I come from a MechE background and work in robotics, so my perspective is biased toward software that interacts with the physical world. But there’s a lot of software that does, either directly or indirectly.
1/
Testing a potentially unpopular opinion that I'm not sure the dev industry is ready for:

Unless you're shipping something like nuclear safety code, you probably don't need a human reviewer for your PRs.
July 25, 2026 at 7:00 PM
Reposted by krishna
Why didn't the eagles just fly Odysseus straight to Ithaca
July 21, 2026 at 4:23 PM
Reposted by krishna
My book, Reinforcement Learning from Human Feedback is done!

This is the book I wish I had when learning to fine-tune, align, & now post-train models since ChatGPT. The resource has been built by me finding time to study and document the fundamentals on nights and weekends since 2024.
July 21, 2026 at 2:29 PM
June 20, 2026 at 7:30 PM
Reposted by krishna
100% agree. if i see “chore” in commit log, im judging you
Stop Using Conventional Commits
You’ve almost certainly encountered Conventional Commits before. It may have reared its ugly head in the changelog of an open source project you’ve used. It may have been the enforced commit format fo...
sumnerevans.com
June 5, 2026 at 6:08 PM
Reposted by krishna
Excellent post on Waymo's handling of safety incidents. open.substack.com/pub/philkoop...
Robotaxi Safety Problems Are The New Normal
Standing down to manage risk is smart. But what needs to happen next?
open.substack.com
May 24, 2026 at 9:35 PM
Reposted by krishna
I'm not gonna touch most of this but two things:
1. The apprenticeship model of science was never supposed to be about the PI's workflow. The point isn't to have research assistants to help to publish stuff faster. Training the next generation researcher *is* the point. Because we care. Allegedly.
Academics Need to Wake Up on AI
Ten theses for folks who haven't noticed the ground shifting under their feet
alexanderkustov.substack.com
March 3, 2026 at 3:14 PM
Reposted by krishna
A new mesh recovery method and model by our lab. My team is currently putting this on our robots, it works really well.
The 🔥🔥Anny roll continues this week with the release of Multi-HMR trained with the Anny body model. Multi-person, single shot Human Mesh Recovery predictions are now made in the open, interpretable parameter space of Anny!
🧑‍🤝‍🧑Multi-HMR code: github.com/naver/multi-...
👉Anny: tinyurl.com/5fsekm9z
February 17, 2026 at 5:29 PM
Reposted by krishna
Want to learn about the latest in robotics research? Like, the real cutting edge, right from researchers? In addition to our youtube channel, I post notes and information about new RoboPapers episodes on Substack here: robopapers.substack.com
RoboPapers | Substack
Chris Paxton & Michael Cho geek out over robotic papers with paper authors. Click to read RoboPapers, a Substack publication with hundreds of subscribers.
robopapers.substack.com
February 16, 2026 at 3:08 AM
Reposted by krishna
if i had more tokens i could have written a shorter reply
February 13, 2026 at 7:00 PM
Reposted by krishna
this is exactly right and explains why most handwringing about building systems we don’t understand is misplaced. pre-LLM software engineering already consisted almost entirely of building systems we did not understand
Nobody knows how the whole system works
One of the surprising (at least to me) consequences of the fall of Twitter is the rise of LinkedIn as a social media site. I saw some interesting posts I wanted to call attention to: First, Simon W…
surfingcomplexity.blog
February 9, 2026 at 2:18 PM
Reposted by krishna
I have updated my tutorial on making Vision Language Action models. This tutorial starts with a basic Transformer and walks people through the steps to transform it into a full VLA that uses PaliGemma as the pretrained VLM. Links below.
February 9, 2026 at 2:15 PM
Reposted by krishna
Loki robotics is cleaning like a person. Doing the work we really want to see automated
February 5, 2026 at 10:48 PM
Reposted by krishna
An attempt to express how I principally use LLMs.

Rotating the Space: On LLMs as a Medium for Thought
sbgeoaiphd.github.io/rotating_the...
January 16, 2026 at 5:16 PM
Reposted by krishna
LLMs automate typing, not thinking.

Mikayla Maki shares her mental model for working with agents, and how she puts it into practice:
zed.dev/blog/on-prog...
On Programming with Agents - Zed Blog
From the Zed Blog: Agents handle typing so we can focus on thinking.
zed.dev
January 23, 2026 at 6:15 PM
Reposted by krishna
Pantograph is building a "daycare for robots" where they can learn unsupervised. These low cost robot crabs are part of the solution. pantograph.com/blog/buildin...
January 20, 2026 at 3:19 PM
Reposted by krishna
a lotta yall still don’t get it

you can use multiple polecats on a single refinery
January 14, 2026 at 11:57 PM
Reposted by krishna
since LLMs save us time coding we have a lot more time to think

since we're thinking about things longer we realize most of our ideas are bad

and since most of our ideas are bad we don't ship as much code
January 11, 2026 at 5:15 AM
Reposted by krishna
January 9, 2026 at 1:40 AM
Reposted by krishna
Just published my annual predictions update, tracking from Jan 1st 2018, with new commentary and new ten year predictions. It is long. rodneybrooks.com/predictions-...
Predictions Scorecard, 2026 January 01 – Rodney Brooks
rodneybrooks.com
January 1, 2026 at 5:32 AM