#agent-loop

#agent-loop

Legacy software, often described as 'big balls of mud,' has accumulated over decades, becoming difficult to maintain and understand. These systems rely on extensive teams to function, despite their outdated technology.

Meta is working on two proprietary frontier models: Avocado, a large language model, and Mango, a multimedia file generator. The open-source variants are expected to be made available at a later date.

Given the right permissions and with the proper plugins, it could create, modify, or delete the user's files and otherwise change things far beyond what most users could achieve with existing models and MCP. Users would use files like USER.MD, MEMORY.MD, SOUL.MD, or HEARTBEAT.MD to give the tool context about its goals and how to work toward them independently, sometimes running for long stretches without direct user input.

Last year I first started thinking about what the future of programming languages might look like now that agentic engineering is a growing thing. Initially I felt that the enormous corpus of pre-existing code would cement existing languages in place but now I'm starting to think the opposite is true. Here I want to outline my thinking on why we are going to see more new programming languages and why there is quite a bit of space for interesting innovation.

AI agents need skills - specific procedural knowledge - to perform tasks well, but they can't teach themselves, a new research suggests. The authors of the research have developed a new benchmark, SkillsBench, which evaluates agentic AI performance on 84 tasks across 11 domains including healthcare, manufacturing, cybersecurity and software engineering. The researchers looked at each task under three conditions: