Sitemap - 2025 - Lossfunk Letters
Future of LLMs might not be Autoregressive
Sequential scaling outperforms parallel scaling for LLMs
Notes on Tiny Recursion Network
Do LLMs know when they've gotten a correct answer?
How do LLMs "think" across languages
What's the point of doing research?
How to choose research problems
Don't tell LLMs you are an AI safety researcher
Tips on writing your first research paper
What is research and how to do it?
Notes on Hierarchal Reasoning Model
Practical tips on building LLM agents
How to approach research in AI
Manifesto for doing good science in AI
How Many Agents Does it Take to Beat PyTorch?(surprisingly not that much)
Don't get tempted to build multi-agents
From an idea to an ML paper in under 1 hour
Reinforcement Learning algorithms summarized