iiinova — where your digital self keeps evolving

Alex Makelov

@amakelov.bsky.social

Mechanistic interpretability Creator of github.com/amakelov/mandala prev. Harvard/MIT machine learning, theoretical computer science, competition math.

Posts Replies Media

Reposted by Alex Makelov

David Bau @davidbau.bsky.social · 20/02/2025

Today we launch a new open research community It is called ARBOR: arborproject.github.io/ please join us. bsky.app/profile/ajy...

1155

Reposted by Alex Makelov

Martin Wattenberg @wattenberg.bsky.social · 23/12/2024

The math benchmarks I want: 1. OopsBench: given a faulty proof with numbered steps, which step contains an unfixable logical flaw? 2. DunnoMath: half the problems are taken from FrontierMath, half are almost certainly unsolvable. Major points off for guessing an answer to an unsolvable problem.

6434

Reposted by Alex Makelov

NDIF Team @ndif-team.bsky.social · 20/12/2024

Large language models show fascinating changes in capability with scaling parameters, but scaling also vastly increases the resources required for experimentation on model internals. NDIF is currently hosting the largest open sourced model, Llama 405b, for YOU to run research on!

152

Alex Makelov @amakelov.bsky.social · 20/12/2024

Talk is cheap. Show me the CoT

020

Alex Makelov @amakelov.bsky.social · 12/12/2024

SaaS (Santa as a Service)

010

Alex Makelov @amakelov.bsky.social · 05/12/2024

Some fun with o1 from OpenAI: there's a math problem I often give to "reasoning" AIs to try them out. It's basically to prove that there's a number less than 1 billion that you can write in 1000 different ways as a sum of 3 squares (precise statement in the pic).

111

Alex Makelov @amakelov.bsky.social · 24/11/2024

yes, this is what mechanistic interpretability research looks like

Cat sitting on a chair in front of a parked black car with its rear wheel removed and a hydraulic jack supporting it

2232