# Sakana AI — String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation

- Company: Sakana AI (sakana.ai)
- Announced: 2026-04-20T15:00:00+00:00
- Category: research-paper
- Subject: Sakana models
- Source: https://sakana.ai/ssot
- Record: https://forck.live/items/4689-string-seed-of-thought-prompting-llms-for-distribution-faithful-and-diverse

Sakana AI announces a prompting technique called String Seed of Thought (SSoT) that reduces output bias and increases diversity in LLM generations, accepted at ICLR2026.

## Evidence

Verbatim from https://sakana.ai/ssot:

> We discovered a prompting technique named String Seed of Thought (SSoT). The method is simple: instruct the LLM to generate a random string in its own output, then manipulate that string to derive its answer. It requires only a small addition to the prompt and no external random number generator.

---

Record: https://forck.live/items/4689-string-seed-of-thought-prompting-llms-for-distribution-faithful-and-diverse
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md