Tag
21 articles
This article explains how pxpipe, an open-source tool, hides text in PNG images to reduce token costs in AI systems like Claude Code and Fable 5, by exploiting differences in API pricing models.
This article explains how language model fine-tuning and personalization work in AI systems, using the comparison between Gemini and Claude's email reply generation as a practical example.
Learn how advanced prompt engineering techniques can dramatically improve AI model performance by strategically designing input prompts to guide large language models toward desired outputs.
Learn how FAPO, a new AI tool from Cisco, automatically improves AI prompts by analyzing each step of a task to make AI systems more accurate and reliable.
Researchers introduce GEPA, a reflective prompt-evolution framework that enhances small language models' performance on multi-step arithmetic problems through structured feedback and multi-component prompt design.
A simple prompt trick involving specifying an artistic style has been shown to improve AI-generated images across different platforms and models.
As AI transforms the workplace, professionals are mastering skills that allow them to become 'AI native'—fluently integrating and optimizing artificial intelligence into their workflows.
This article explains how to build a complete Langfuse observability and evaluation pipeline for LLM development, covering tracing, prompt management, scoring, and experimentation.
51% of professionals report that AI workslop lowers their productivity, highlighting the need for better AI implementation strategies. Experts suggest two key steps to combat this issue.
This article explores how advanced AI coding assistants like Codex work, using a real-world example of generating Linux window manager configurations. It explains the underlying technology and reveals important limitations of current AI systems.
Learn to build an AI-native workflow system that combines data engineering, prompt engineering, and language model integration - skills in high demand in today's job market.
This article explores advanced prompting techniques for large language models, including negative constraints, structured JSON outputs, and multi-hypothesis verbalized sampling, essential for reliable production deployment.
