DeepSeekR1
Artificial Intelligence
The best way to Train LLMs to “Think” (o1 & DeepSeek-R1)
In September 2024, OpenAI released its o1 model, trained on large-scale reinforcement learning, giving it “advanced reasoning” capabilities. Unfortunately, the small print of how they pulled this off were never shared publicly. Today, nevertheless,...
Artificial Intelligence
DeepSeek-R1 Red Teaming Report: Alarming Security and Ethical Risks Uncovered
A recent red teaming evaluation conducted by Enkrypt AI has revealed significant security risks, ethical concerns, and vulnerabilities in DeepSeek-R1. The findings, detailed within the January 2025 Red Teaming Report, highlight the model's susceptibility...
Artificial Intelligence
DeepSeek-R1: Transforming AI Reasoning with Reinforcement Learning
DeepSeek-R1 is the groundbreaking reasoning model introduced by China-based DeepSeek AI Lab. This model sets a brand new benchmark in reasoning capabilities for open-source AI. As detailed within the accompanying research paper, DeepSeek-R1 evolves...
Recent posts
