about.subtitle
This section features materials dedicated to the transition from static algorithms to autonomous systems capable of goal-setting and long-term planning. We view generative agents not merely as a software interface, but as a new layer in the architecture of human-technology interaction. Here, we analyze their behavioral mechanics: from the capacity for reflection and memory formation to social interactions within simulated environments.
OpenAI has introduced GPT-5.4, a new model with enhanced capabilities for working with code, tools, and extensive volumes of text.
Amazon Bedrock now supports persistent orchestration and memory for AI agents, changing the approach to building multi-step workflows.
OpenHands has introduced a tool for automatically fixing vulnerabilities in code: an AI agent autonomously analyzes the problem and provides a ready-to-implement solution.
Cursor has introduced Bugbot Autofix, a tool that automatically corrects errors found in code by launching separate cloud agents to handle the task.
Cursor has released an update where AI agents can now independently run and test code directly on a virtual machine.
AI: Events
Technical context • Development
Two AI agents can create optimized CUDA kernels to speed up operations straight from a task description. Let's dive into what this means for people working with models.
Don’t miss a single experiment!
Subscribe to our Telegram channel —
we regularly post announcements of new books, articles, and interviews.