Can Coding Agents Learn?
Abject founder Maximillian Mempko argues that AI coding agents cannot learn, contrasting two existing models—Orchestrated Agents and Role Agents—and proposing a third, more autonomous approach. Mempko…
Abject founder Maximillian Mempko argues that AI coding agents cannot learn, contrasting two existing models—Orchestrated Agents and Role Agents—and proposing a third, more autonomous approach. Mempko…
A new measurement study of cache keepalive economics across Anthropic, OpenAI, Gemini, and DeepSeek shows that the common practice of pinging every 30 seconds costs 8 times more than necessary, with t…
A new measurement study of prompt cache keepalive economics across Anthropic, OpenAI, Gemini, and DeepSeek finds that the common practice of pinging every 30 seconds costs 8x more than necessary, and …
Abject project creator Maxim Khitrov argues that the true essence of object-oriented programming, as defined by Alan Kay, is messaging and late binding, not classes or hierarchies. The Abject project …
At the ninth MLSys conference in Seattle, researchers and industry leaders focused overwhelmingly on improving the efficiency of training and deploying large language models, with specialized hardware…
A 30-year programming veteran argues that artificial intelligence is dismantling the information monopolies that have long justified high salaries for tech workers, doctors, and lawyers. The author co…