# Sakana AI — Can LLMs invent better ways to train LLMs?

- Company: Sakana AI (sakana.ai)
- Announced: 2024-06-12T15:00:00+00:00
- Category: research-paper
- Subject: Sakana models
- Source: https://sakana.ai/llm-squared
- Record: https://forck.live/items/4730-can-llms-invent-better-ways-to-train-llms

Sakana AI releases a research report on using LLMs to discover preference optimization algorithms, including the state-of-the-art DiscoPOP algorithm, and open-sources the codebase and model checkpoints.

## Evidence

Verbatim from https://sakana.ai/llm-squared:

> we’re excited to release our report, Discovering Preference Optimization Algorithms with and for Large Language Models .

---

Record: https://forck.live/items/4730-can-llms-invent-better-ways-to-train-llms
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md