hotai.news
← Back to AI Newsflash
AI News / Event details
x.com · Published

Research: LLM moral choices lack stable value rankings

Automated summary · Based on collected summaries; not individually verified
Prepared by HotAI

What happened

A new study finds that LLMs often lack stable value rankings when making moral choices; averaging their answers creates a false, human-like hierarchy of morality. Researchers tested five LLMs—including GPT-5.2, Gemini, and DeepSeek—on paired moral violations, extracting probabilities directly from next-token outputs.

Background

What Is DeepSeek? Hosted Models and Open Weights

DeepSeek is a generative AI company and model brand, and the name is also commonly used for its chat app. It offers hosted APIs and has released model weights for self-hosting. A hosted API name may be an alias pointing to an updated model, while downloaded weights correspond to a particular release. This distinction helps determine whether old code still calls the original model and whether a hosted experience can be reproduced locally.

What Is Gemini? Multimodal Models and App Features

Gemini is Google’s generative AI model family, with particular versions accepting text and multiple media types. Gemini Apps is the application for chatting and uploading files. Multimodality must distinguish input types from generated content. For example, Gemini 4 Argon accepts audio and video but outputs text; understanding video does not imply generating it. Readers seeking local model weights should also distinguish the separate Gemma family.

Reading notes

The event summary comes from collected excerpts. Background passages quote existing HotAI articles to explain terms and do not establish new facts about this event. Check the original sources for product results, conditions and subsequent updates.

Original source

Sources and collection timeline

SourceReport titleOriginal publication timeCollected by HotAI
x.comResearch: LLM moral choices lack stable value rankings2026-11-11 12:082026-11-11 12:22