Put your AI agents to work with these 5 killer tasks
The New York Times suggests five tasks, such as applying for jobs or booking hard-to-get restaurant tables, where agents like Meta's Muse and OpenAI's dots can prove their worth.
Related stories
Anthropic says one AI agent beats many subagents now that models can handle complexity alone
Anthropic is advising companies to consider merging subagents into a single agent that loads context as needed. In one comparison, the single-agent setup ran about twice as fast, and Anthropic has published a migration kit on GitHub.
OpenMobile-2 shows open-source smartphone agents can rival proprietary models
The researchers behind OpenMobile-2 argue smartphone agents improve by training on many different apps rather than on more data. They built an open environment with over 110 apps, including 35 replicas of popular ones, and say their model scores highest among open agents on real Android devices.
Microsoft open-sources Agensh, a multi-agent harness for 1,024 agents
Microsoft Research has released Agensh, a multi-agent harness with no central orchestrator in which self-organising workers share a Git repository, a chat and a findings board. On ProgramBench, with a six-hour budget, it scaled from one agent to 1,024.
Cognition open-sources an agent plugin to help secure systems against this week's critical flaws
Cognition has released the Devin Vulnerability Fixes plugin, three MIT-licensed agent skills that inventory, patch and test PHP, Node.js and self-managed GitLab deployments affected by this week's critical remote code execution flaws. The plugin then opens one pull request per repository.
Nanbeige releases Nanbeige4.3-33B, an open agentic coding model
Nanbeige LLM Lab has released Nanbeige4.3-33B, a 33-billion-parameter dense model under Apache 2.0 with a 512K context window. It scores 80.9 on Terminal-Bench 2.1 and will be used to teach the forthcoming Nanbeige4.3-3B.