AI Agents

Large language models may have learned knowledge that’s relevant to a given prompt, but they don’t always recall it consistently. Fine-tuning a model to search its parameters as though it were searching the web can help it find knowledge in its own weights.

Independent cybersecurity researchers pushed back on a report by Anthropic that claimed hackers had used its Claude Code agentic coding system to perpetrate an unprecedented automated cyberattack.

The latest open-weights large language model from Moonshot AI challenges top proprietary LLMs at agentic tasks by executing hundreds of tool calls sequentially and pausing to think between each.

An open-weights model from Shanghai-based MiniMax challenges top proprietary models on key benchmarks for coding and agentic tasks.

Honing an agent’s prompt can yield better results than fine-tuning the underlying large language model via reinforcement learning.

Anthropic updated its mid-size Claude Sonnet model, making it the first member of the Claude family to reach version 4.5. It also enhanced the Claude Code agentic coding tool with long-desired features.

AI agents are getting in on the action of online sports gambling.

Google launched an open protocol for agentic payments that enables agents based on any large language model to purchase items over the internet.

Swarms of drones that coordinate with one another autonomously have become a battlefield staple in Ukraine.

A growing private school system replaces the typical 6-hour school day with 2 hours of personalized, AI-assisted education. 

Autonomous agents built on large language models introduce distinct security concerns. Researchers designed a system to protect agents from common vulnerabilities.

Google’s latest smartphone sports an AI assistant that anticipates the user’s needs and presents helpful information without prompting.

A bottleneck in fine-tuning large language models for software engineering is building a dataset that can show them how to edit code, search for subroutines, write test scripts, control a terminal, manage a file system, and so on. Researchers built a pipeline that produces such data automatically.

An autonomous robot performed intricate surgical operations without human intervention.

LLMs can struggle with difficult algorithmic or scientific challenges when asked to solve them in a single attempt. An agentic workflow improved one-shot performance on hard problems both theoretical and practical.