# Together AI — What do LLMs think when you don't tell them what to think about?

- Company: Together AI (together.ai)
- Announced: 2026-02-06T00:00:00+00:00
- Category: research-paper
- Subject: Inference platform
- Source: https://www.together.ai/blog/what-llms-think
- Record: https://forck.live/items/2381-what-do-llms-think-when-you-don-t-tell-them-what-to-think-about

A study of near-unconstrained LLM generation reveals that different model families exhibit distinct topical preferences: GPT-OSS favors programming and math, Llama leans literary, DeepSeek often produces religious content, and Qwen tends toward multiple-choice questions.

## Evidence

Verbatim from https://www.together.ai/blog/what-llms-think:

> We study the behavior of LLMs using minimal, topic-neutral prompts.

---

Record: https://forck.live/items/2381-what-do-llms-think-when-you-don-t-tell-them-what-to-think-about
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md