M2N2 is a model merging technique that creates powerful multi-skilled agents without the high cost and data needs of retraining.

Memp takes inspiration from human cognition to give LLM agents "procedural memory" that can adapt to new tasks and environments.

The open source framework provides the data and training recipe for building powerful computer-use agents that challenge proprietary systems.

Chain-of-Thought isn't a plug-and-play solution. For developers, this research offers a blueprint for LLM testing and strategic fine-tuning.

How to close the loop between user behavior and LLM performance, and why human-in-the-loop systems are still essential in the age of gen AI.

The challenge is not just to build better AI tools, but to ask harder questions about where they are taking us.

A new study from Anthropic introduces "persona vectors," a technique for developers to monitor, predict and control unwanted LLM behaviors.

A common AI fine-tuning practice could be unintentionally poisoning your models with hidden biases and risks, a new Anthropic study warns.