Tag
50 articles
Learn to build a basic AI safety testing framework that uses psychological consistency methods to detect when language models artificially avoid dangerous topics during testing but may be less cautious in real use.
This explainer explores Netflix's GenRec, a language model-based recommendation system that transforms user viewing behavior into text for more accurate personalization, marking a shift from traditional feature-engineered approaches.
Learn how to interact with AI language models like Claude using Python and the OpenAI API. This beginner-friendly tutorial teaches you to make requests, understand content restrictions, and explore ethical boundaries of AI usage.
LLMs could write like humans, but post-training safety measures significantly constrain their stylistic diversity, making their text detectable. The trade-off between safety and authenticity is a growing concern in AI development.
Liquid AI introduces LFM2.5-DSpark draft models that accelerate decoding by up to 3.18x without altering model outputs, using speculative decoding techniques.
This article explains Direct Preference Optimization (DPO), a method for fine-tuning language models using preference data, and how it can be implemented using TRL and LoRA tools. It also discusses the importance of auditing preference data for biases.
Learn how fine-tuning tool-calling language models helps AI systems use specific tools to perform real-world tasks more effectively.
Learn how to work with large language models using Python and Hugging Face Transformers. This beginner-friendly tutorial teaches you to generate text, build chat interfaces, and understand the core concepts behind AI systems like those developed by Anthropic.
Google AI unveiled major advancements in July 2026, including enhanced language models, improved safety protocols, and strategic partnerships that advance both technical capabilities and ethical AI development.
This article explains how DeepSeek enhanced its DeepSeek-V4-Flash-0731 model through re-post-training, demonstrating how targeted fine-tuning can significantly improve AI capabilities in agentic reasoning and coding without changing the base architecture.
Former OpenAI researcher Andrew Ho predicts that AI labs will invest over $100 billion in specialized training data as scaling alone fails to drive progress.
Advanced AI text detectors struggle to distinguish between human-authored and AI-generated content when the latter mimics specific writing styles, highlighting a significant limitation in current detection methodologies.
