--- title: "What do LLMs think when you don't tell them what to think about?" url: https://daily.dev/posts/what-do-llms-think-when-you-don-t-tell-them-what-to-think-about--krez1j9vi source_url: https://www.together.ai/blog/what-llms-think type: article source: "Together AI" published: 2026-05-31T07:40:55.704Z updated: 2026-05-31T08:25:09.042Z tags: ["llm", "ai-safety"] reading_time: 6 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # What do LLMs think when you don't tell them what to think about? **[Together AI](https://daily.dev/sources/togetherai)** · 6 min read · 0 upvotes · 0 comments ## Summary Researchers from Together.ai studied what LLMs generate when given minimal, topic-neutral prompts with no chat templates or system instructions. The findings reveal that different model families have distinct 'knowledge priors': GPT-OSS defaults heavily to programming (27.1%) and mathematics (24.6%), Llama favors literary and narrative content, DeepSeek generates religious content at elevated rates, and Qwen frequently outputs multiple-choice exam questions. These topical biases are consistent across different prompts, embeddings, and labelers, suggesting they reflect population-level fingerprints rather than noise. Additionally, depth differs by family — GPT-OSS produces expert-level content 68.2% of the time, while Llama and Qwen skew toward basic material. Degenerate outputs (repetitive or meaningless text) also carry model-specific signatures, including Llama emitting real personal social media URLs, raising safety and privacy concerns. The research argues that near-unconstrained generation exposes model defaults that standard benchmarks systematically miss. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Researchers discover a shortcoming that makes LLMs less reliable](https://daily.dev/posts/researchers-discover-a-shortcoming-that-makes-llms-less-reliable-wiiiapmcn) · MIT News · 2 upvotes · 0 comments - [LLMs are stuck in a groupthink rut. This startup is trying to get them out.](https://daily.dev/posts/llms-are-stuck-in-a-groupthink-rut-this-startup-is-trying-to-get-them-out--2otelcdhy) · MIT Technology Review · 1 upvotes · 0 comments - [Should We Use LLMs As If They Were Swiss Knives?](https://daily.dev/posts/should-we-use-llms-as-if-they-were-swiss-knives--e3ejswdqw) · Towards Data Science · 0 upvotes · 0 comments - [LLMs struggle to distinguish between facts and beliefs](https://daily.dev/posts/llms-struggle-to-distinguish-between-facts-and-beliefs-prusuuk6y) · The Register · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-safety](https://daily.dev/tags/ai-safety) [View this post on daily.dev](https://daily.dev/posts/what-do-llms-think-when-you-don-t-tell-them-what-to-think-about--krez1j9vi)