Scaling long-running autonomous coding

kept by eddie jan 15

Cursor's multi-agent system, using planners and workers, scaled to run hundreds of autonomous coding agents for weeks on projects like building a browser, finding simpler coordination beats complex distributed-computing approaches.

Better AI models enable more ambitious work
A University of Chicago study of 500 companies found AI usage rose 44% as models improved, with developers shifting to more complex and cross-system tasks.
also on Opus 4.5, GPT-5.2, Cursor, #ai-coding, #software-engineering, #productivity, #developer-tools
When AI writes almost all code, what happens to software engineering?
AI coding tools like Opus 4.5 and GPT-5.2 now generate 90%+ of code, fundamentally reshaping software engineering roles and skills.
also on Opus 4.5, GPT-5.2, #ai-coding, #software-engineering, #productivity, #developer-tools
Use multiple models - by Nathan Lambert - Interconnects
To get the most out of AI in 2026, the author recommends using multiple models for different tasks as each model has jagged capabilities.
also on GPT-5.2, #ai-coding, #productivity
Claude Opus 4.6
Anthropic releases Claude Opus 4.6 with improved coding, 1M token context window, and agent team collaboration features.
also on GPT-5.2, #ai-coding, #developer-tools