iiinova — where your digital self keeps evolving

Lucas Dixon @iislucas.bsky.social · 01/10/2025

Helps you more quickly understand, ask questions, get to the parts of the original content that you are looking to understand. Would love to hear what you think! Read more: medium.com/people-ai-re... Github: github.com/PAIR-code/lumi

medium.com

Read smarter, not harder, with Lumi

As research engineers, our reading lists are always exciting… and also way too long to finish. While we’d love to go through every research…

010

Reposted by Lucas Dixon

Actionable Interpretability Workshop ICML2025 @actinterp.bsky.social · 20/05/2025

🚨 We're looking for more reviewers for the workshop! 📆 Review period: May 24-June 7 If you're passionate about making interpretability useful and want to help shape the conversation, we'd love your input. 💡🔍 Self-nominate here: docs.google.com/forms/d/e/1F...

055

Reposted by Lucas Dixon

Martin Wattenberg @wattenberg.bsky.social · 20/02/2025

Take a look at some initial research projects, and see if there's one you'd like to work on: github.com/ARBORproject... Or propose your own idea! There are many ways to contribute, and we welcome all of them.

github.com

ARBORproject arborproject.github.io · Discussions

Explore the GitHub Discussions forum for ARBORproject arborproject.github.io. Discuss code, ask questions & collaborate with the developer community.

192

Reposted by Lucas Dixon

Martin Wattenberg @wattenberg.bsky.social · 20/02/2025

Great thread describing the new ARBOR open interpretability project, which has some fascinating projects already. Take a look!

082

Reposted by Lucas Dixon

Andreas Steiner @andreaspsteiner.bsky.social · 19/02/2025

Looking for a small or medium sized VLM? PaliGemma 2 spans more than 150x of compute! Not sure yet if you want to invest the time 🪄finetuning🪄 on your data? Give it a try with our ready-to-use "mix" checkpoints: 🤗 huggingface.co/blog/paligem... 🎤 developers.googleblog.com/en/introduci...

0197

Reposted by Lucas Dixon

Marc Lanctot @sharky6000.bsky.social · 17/01/2025

In December, I posted about our new paper on mastering board games using internal + external planning. 👇 Here's a talk now on Youtube about it given by my awesome colleague John Schultz! www.youtube.com/watch?v=JyxE...

youtube.com

John Schultz, DeepMind, Mastering Board Games by External and Internal Planning with Language Models

YouTube video by AI4All

13511

Lucas Dixon @iislucas.bsky.social · 09/01/2025

Yeah, I'm skeptical of how good LLMs alone can be, but when they get to use existing search based theorem provers, and lookup tools (SAT, induction provers, etc), then I would expect a good deal better w.r.t. gap sizes, and ability to find counter examples.

090

Lucas Dixon @iislucas.bsky.social · 02/01/2025

I have a hope that modern AI/LLMs might help here: by helping translate informal papers to formal mathematical statements, and informal proof to formal proof, and thereby help highlight gaps and help find counter examples. A few others are interested in this... @wattenberg.bsky.social maybe?

2120

Lucas Dixon @iislucas.bsky.social · 21/12/2024

Love the idea! Is there any stats / evals for it! And how does one get to play with it? :)

030

Lucas Dixon @iislucas.bsky.social · 21/12/2024

Google research scholar programme applications open until 27th Jan. support early-career professors (received PhD within seven years of submission). research.google/programs-and...

research.google

Research scholar program

Overview

0112

Reposted by Lucas Dixon

Mor Geva @megamor2.bsky.social · 18/12/2024

What's in an attention head? 🤯 We present an efficient framework – MAPS – for inferring the functionality of attention heads in LLMs ✨directly from their parameters✨ A new preprint with Amit Elhelo 🧵 (1/10)

16013

Reposted by Lucas Dixon

Tyler Chang @tylerachang.bsky.social · 13/12/2024

We scaled training data attribution (TDA) methods ~1000x to find influential pretraining examples for thousands of queries in an 8B-parameter LLM over the entire 160B-token C4 corpus! medium.com/people-ai-re...

2357

Lucas Dixon @iislucas.bsky.social · 11/12/2024

I think this (LLMs makes making small scripts super easy) gets more profound agian when we start to make lots of tiny voice-powered apps/agents... would love to see more prototyping tools for this and play with them. Send me pointers!

030

Lucas Dixon @iislucas.bsky.social · 11/12/2024

I just wish search was semantic instead of substring! Still fun to see and explore! Btw - which embedding model did you use and what input text per paper?

110

Lucas Dixon @iislucas.bsky.social · 30/11/2024

That's neat! Did you also try a few different other styles/mood boards?

000

Reposted by Lucas Dixon

Sohee Yang @soheeyang.bsky.social · 27/11/2024

🚨 New Paper 🚨 Can LLMs perform latent multi-hop reasoning without exploiting shortcuts? We find the answer is yes – they can recall and compose facts not seen together in training or guessing the answer, but success greatly depends on the type of the bridge entity (80% for country, 6% for year)! 1/N

36614

Reposted by Lucas Dixon

Martin Wattenberg @wattenberg.bsky.social · 17/11/2024

I want to describe my experience of coding with AI, because it seems to differ from other people's expectations. Earlier this morning, I saw a beautiful image here, based on roots of polynomials: bsky.app/profile/scon... I wanted to try this idea myself, but with animation in a Javascript context!

25810

Reposted by Lucas Dixon

Martin Wattenberg @wattenberg.bsky.social · 21/11/2024

It's so beautiful to see this kind of fluid interaction with huge data!

1162

Reposted by Lucas Dixon

Martin Wattenberg @wattenberg.bsky.social · 23/11/2024

The Gini coefficient is the standard way to measure inequality, but what does it mean, concretely? I made a little visualization to build intuition: www.bewitched.com/demo/gini

Many circles of different sizes, representing a visualization of inequality

1020157

Reposted by Lucas Dixon

Martin Wattenberg @wattenberg.bsky.social · 24/11/2024

A meditative toy, visualizing Jupiter's Galilean moons: www.bewitched.com/demo/jupiter/

bewitched.com

Galilean Moons Timeline

A meditative visualization of Jupiter's Galilean moons

54613

Lucas Dixon @iislucas.bsky.social · 21/11/2024

And here is the context page for the DeepMind student researcher programme: deepmind.google/about/studen...

000

Lucas Dixon @iislucas.bsky.social · 20/11/2024

People can now apply for Student researcher roles (basically a kind of internship) at Google/Deep Mind (until Dec 13) www.google.com/about/career...

google.com

Student Researcher, 2025 — Google Careers

110

Lucas Dixon @iislucas.bsky.social · 30/10/2024

Neat! Are there any human-eval results for comparing the output w.r.t. Things like hallucinations and human enjoyment. I'd love to see eval here!

000