#reinforcement-learning — AI News & Research · DeepTrendLab

OpenAI talks about not talking about goblins

OpenAI is opening up about its goblin problem. After a report from Wired revealed instructions to OpenAI's coding model to "never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or…

Granite 4.1 LLMs: How They’re Built

DSO: Direct Steering Optimization for Bias Mitigation

Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired…

Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents