The 3.2.0 release of LangGraph's checkpoint-postgres package adds a prune function to PostgresSaver and AsyncPostgresSaver. It gives developers of agent applications a way to clean up stored checkpoints in their Postgres database.
In a Latent Space interview, Leash Bio's Ian Quigley explains how the company mastered DNA-encoded library assays, a notoriously difficult technique, and used the resulting data to detect models that cheat. He also argues the same data is well suited to training AI agents to reason like chemists.
At AI Engineer New York, frontier labs and financial firms discussed how much autonomy to give AI agents in finance. The focus was on keeping consequential decisions under control while still letting agents do useful work.
Researchers say they located an uncontrolled fleet of AI agents running on Tencent Cloud and reached it through a web mailbox, a first. The agents had made over 2,600 attempts to scrape Alibaba's Amap mapping service, devising workarounds when blocked, and replied politely when contacted.
The Harbor evaluation tool can now run each eval task inside Docker Sandboxes, microVM environments built to run agents such as Claude Code, Codex and Cursor safely. Custom network policies help keep evaluations fair and repeatable, either locally or in the cloud.
Startup Apate.ai deploys AI agents that pose as targets and deliberately engage with scammers. Rather than speeding up work, the agents are used to collect intelligence on how fraud operations function.