AI news for platform & agent engineers
Ranked brief · refreshes every 2 hours
Skills provide agents with reusable experience to guide future decisions without modifying the underlying model. However, coding trajectories are often entangled with task- and repository-specific contexts, making it... Context & related coverage →
Uber has introduced Normalized Compute Units (NCUs) to make CPU allocation more consistent across its highly heterogeneous server fleet. By Craig Risi Context & related coverage →
Recursive self-improvement (RSI) requires an agentic system to design, train, and evaluate its own successor. Data-driven post-training is a central part of that loop, yet existing evaluations measure it on a single b... Context & related coverage →
Single-document corpus poisoning under black-box access poses a severe threat to Retrieval-Augmented Generation (RAG). However, existing attacks predominantly rely on explicit factual refutations or imperative instruc... Context & related coverage →
Long-horizon LLM agents interact with their environments through complete assistant turns while generating each action token by token. We observe that critic values vary primarily across turns, motivating optimization... Context & related coverage →
Error-targeted learning gives a legible way to improve a model: identify specific weaknesses of the model, train the model to fix these weaknesses, and check whether the weaknesses are fixed. We study how to apply err... Context & related coverage →