Alex Makelov
@amakelov.bsky.social
Mechanistic interpretability
Creator of https://github.com/amakelov/mandala
prev. Harvard/MIT
machine learning, theoretical computer science, competition math.
Creator of https://github.com/amakelov/mandala
prev. Harvard/MIT
machine learning, theoretical computer science, competition math.
Reposted by Alex Makelov
Today we launch a new open research community
It is called ARBOR:
arborproject.github.io/
please join us.
bsky.app/profile/ajy...
It is called ARBOR:
arborproject.github.io/
please join us.
bsky.app/profile/ajy...
February 20, 2025 at 10:15 PM
Today we launch a new open research community
It is called ARBOR:
arborproject.github.io/
please join us.
bsky.app/profile/ajy...
It is called ARBOR:
arborproject.github.io/
please join us.
bsky.app/profile/ajy...
Reposted by Alex Makelov
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.
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.
December 23, 2024 at 2:21 PM
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.
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.
Reposted by Alex Makelov
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!
December 20, 2024 at 7:49 PM
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!
Talk is cheap. Show me the CoT
December 20, 2024 at 7:46 PM
Talk is cheap. Show me the CoT
SaaS (Santa as a Service)
December 12, 2024 at 6:18 PM
SaaS (Santa as a Service)
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).
December 5, 2024 at 9:15 PM
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).
yes, this is what mechanistic interpretability research looks like
November 24, 2024 at 7:51 PM
yes, this is what mechanistic interpretability research looks like