Tag
Fence proposes using Small Language Models trained on high-quality synthetic data as specialized guardrails for LLM applications, demonstrating performance gains over prompt-based LLM guardrails.
A perspective on how task complexity (measured in bits to specify a task) creates opportunities for AI startups to build software scaffolding around frontier models, especially for high-complexity and hard-to-verify tasks.
Manning Books announces a new early access book 'Building LLM Applications with DSPy', teaching how to use the DSPy framework to optimize LLM prompts with Python. The book is 50% off through June 3rd.
This tweet promotes a library that enables full observability and automatic analytics for LLM-based applications with just one line of code, claiming it provides valuable information for free.
A team is winning local trivia nights using an AI model with continuous time awareness.
Tim Davis, head of Modular, shares his experience building an autonomous code-writing system called Compound Loop and argues that software development is shifting from deterministic to probabilistic systems, with AI agents enabling a '24-7 employee' model where human operators coordinate rather than type, while roles are splitting between high-leverage positions and lower-value agent-wrangling work.