Lossfunk Letters

Notes on Tiny Recursion Network

aka how a 7M parameter network gets SOTA on Sudoku-Extreme with 87% accuracy

Oct 31 • 

Paras Chopra

3

Do LLMs know when they've gotten a correct answer?

We show they do and then use it to help cut reasoning cost (in tokens) by up to 50% without losing accuracy

Oct 29 • 

Aman Sharma

11

How do LLMs "think" across languages

Performance of LLMs differ based on language on reasoning tasks and this difference varies for each task.

Oct 28 • 

Shourya

13

5

What's the point of doing research?

The fun of the struggle is the point

Oct 17 • 

Paras Chopra

27

2

September 2025

How to choose research problems

TLDR: balance between what your heart says and what the community will value

Sep 10 • 

Paras Chopra

9

1

Don't tell LLMs you are an AI safety researcher

Adding “for AI safety research” increased refusals on a harmless paraphrasing task for some top models. Conservative, aligned public models might be…

Sep 5 • 

Dhruv Trehan

7

4

August 2025

Tips on writing your first research paper

aka, how to increase your odds of acceptance at an AI/ML conference

Aug 29 • 

Paras Chopra

9

What is research and how to do it?

or, can you teach an AI how to do good research?

Aug 12 • 

Paras Chopra

46

7

Notes on Hierarchal Reasoning Model

aka what can we learn from the brain!

Aug 6 • 

Paras Chopra

9

1

July 2025

Practical tips on building LLM agents

Resources we stumbled upon to help build your next agent

Jul 22 • 

Paras Chopra

60

2

How to approach research in AI

How we advice our interns to go about research

Jul 11 • 

Paras Chopra

10

Manifesto for doing good science in AI

aka, why building things != doing research

Jul 7 • 

Paras Chopra

52

3