Archive - Lossfunk Letters

Practical tips on building LLM agents

Resources we stumbled upon to help build your next agent

Jul 22 •

How to approach research in AI

How we advice our interns to go about research

Jul 11 •

Manifesto for doing good science in AI

aka, why building things != doing research

Jul 7 •

How Many Agents Does it Take to Beat PyTorch?(surprisingly not that much)

Or: What happens when you give AI-agents a GPU and tell them to make it go brrr.

Jul 4 •

and

Don't get tempted to build multi-agents

Linear, continuous LLM flows are all you need

Jul 3 •

From an idea to an ML paper in under 1 hour

or, vibe-researching using Gemini-CLI to find logical inconsistencies in text

Jul 1 •

June 2025

Reinforcement Learning algorithms summarized

Everything you wanted to learn about RL, but were too afraid to ask!

Jun 18 •

May 2025

AI is the future of Market Efficiency

The coming era of Intelligence Arbitrages

May 21 •

and

Welcome to the world of Lossfunk

Your friendly neighborhood AI lab

May 3 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts