Reading up on Cognition

Autoresearch uses outer loops with feedback signals and human input to let agents improve and maintain systems, reducing bottlenecks while keeping humans central.

Cognition's FrontierCode benchmark measures code mergeability, finding even top models like Claude Opus 4.8 score only 13.4% on its hardest 50 tasks.

Cognition CEO Scott Wu argues AI coding agents like Devin will expand software creation rather than eliminate engineering jobs despite industry layoffs and competition.

Individual AI tools boost personal productivity but fail to improve firm-level outcomes until organizations redesign their processes and coordination structures around AI.

Cognition uses its own Devin agents across Slack, Linear, and CLI to merge 659 PRs weekly, automating code review, bug triage, and design-system audits.

Cognition launches Devin Review, an AI tool that organizes diffs, catches bugs, and enables live chat to solve the code-review bottleneck created by coding agents.

A developer built an ASCII renderer that uses shape vectors and contrast enhancement to achieve sharp edges, overcoming blurriness from treating characters as pixels.

A developer demonstrates how to build a custom async coding agent by combining Slack, Modal, GitHub, and Claude Code/Codex headless mode, arguing this makes cloud coding agents like Devin undifferentiated.