←
Tim Vieira2,590 posts
Tim Vieira avatar

Tim Vieira

@xtimv

machine learning, reinforcement learning, programming languages, handstands (he/him)

◷ Joined June 2009▧ 156 Photos and videos
Tim Vieira avatar
Tim Vieira@xtimv·5 Nov 2016

When you say, "This is a reinforcement learning problem," you should say it with the same excitement as "This is NP-hard."

Tim Vieira avatar
Tim Vieira@xtimv·Nov 1

How do you test a randomized algorithm? Running it a million times might not be enough. I wrote about a few testing strategies, culminating in a neat trick: enumerate every possible execution trace and check correctness exactly. timvieira.github.io/testing-…

Post attachment
Tim Vieira avatar
Tim Vieira@xtimv·Oct 28

Conditional Poisson Sampling (CPS) CPS is a distribution over fixed-size subsets in which each subset’s probability is proportional to the product of its items’ weights. This one has lots of fun JavaScript and math. timvieira.github.io/conditio…

Post attachment
Sasha Rush avatar
⟳ Tim Vieira retweeted
Sasha Rush@srush_nlp·Oct 19

Late to the party, but this blog post is excellent. Arguably the way people should first learn neural networks.

how much can models remember? there’s a neat perspective on neural networks that deserves to be more widely known here’s how you could have invented every layer of the transformer from memory (1/n) from my new blog post!

David Hall avatar
⟳ Tim Vieira retweeted
David Hall@dlwh·Oct 15

I've been thinking about where the data for the next generation of open models will come from. The internet gave us a remarkable commons for pretraining. Posttraining is different: it consumes tasks, not documents. And that commons doesn't exist. Not yet. openathena.ai/blog/there-is-…

Nicolò Cesa-Bianchi avatar
⟳ Tim Vieira retweeted
Nicolò Cesa-Bianchi@NicoloCB·Oct 7

My dream had always been to prove beautiful theorems as the AI agents unloaded my dishwasher. Well, it went the wrong way... 😂

Percy Liang avatar
⟳ Tim Vieira retweeted
Percy Liang@percyliang·Oct 6

🚢Marin 535B-A23B training has crossed the halfway mark! Some observations and learnings so far:

Post attachment
Sasha Rush avatar
⟳ Tim Vieira retweeted
Sasha Rush@srush_nlp·Oct 1

Sampling to Reinforce (srush.github.io/sampling-to-…) An elementary tutorial on sampling w/o randomness with a focus on gaining intuition for variance reduction as the key challenge.

0:06
Sasha Rush avatar
⟳ Tim Vieira retweeted
Sasha Rush@srush_nlp·Sep 15

Lean Verified Transformers (srush.github.io/lean-transfo…) In which we prove a bunch of Transformer invariants from scratch in Lean, and speculate about how hard it would be to do that for the rest of the world's code.

Post attachment
Geoffrey Litt avatar
⟳ Tim Vieira retweeted
Geoffrey Litt@geoffreylitt·Jul 2

Hot take: I think it's still important to understand the code that our agents write! In this mega thread (based on my AIE talk today), I will explain why that's the case, and show some ideas for how to efficiently understand code. Alright, let's dive in. 1/

Post attachment
Mark Schmidt avatar
⟳ Tim Vieira retweeted
Mark Schmidt@MarkSchmidtUBC·Jul 21

Slides from my ICML tutorial "Is numerical optimization theory irrelevant to machine learning practice in 2026?": cs.ubc.ca/~schmidtm/Document… (Updated to fix some typos, incorporate feedback, and add some things I did not have time for. Will link to the video here when posted.)

Post attachmentPost attachmentPost attachmentPost attachment
Rico Angell avatar
⟳ Tim Vieira retweeted
Rico Angell@rico_angell·May 14

It’s deployment time! You’ve done the pre-deployment evals. You THINK your model is safe, so you ship it 🚀 🚨 After deployment, reports of misbehavior start trickling in What happened?? How could you have caught it?? 🤔 @icmlconf 2026 Spotlight! 🧵

Post attachment