Reading up on Devin
12 deep · digging since dec 23, 25
- “It’s Hard to Eval” Is a Product Smell – Hamel's Blog
Products that are hard to evaluate programmatically are likely hard for users to verify, so design for verification first.
- The Untrainable - Sarah Guo
As AI models commoditize measurable tasks, lasting value lies in 'untrainable' work requiring private data, trust, organizational change, and domain-specific authority.
- Introducing FrontierCode
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.
- Inside the grind: The SF startup racing to build an AI software engineer
Cognition CEO Scott Wu argues AI coding agents like Devin will expand software creation rather than eliminate engineering jobs despite industry layoffs and competition.
- Cognition | Introducing Devin 2.2
Devin 2.2 adds end-to-end desktop testing, self-review autofix, and 3x faster startup so the agent can autonomously plan, code, test, and fix code.
- How Cognition Uses Devin to Build Devin - by Nader Dabit
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.
- Devin (the Developer)
Devin is an AI software engineer that autonomously codes, debugs, and deploys applications from natural language prompts.
- Ask HN: COBOL devs, how are AI coding affecting your work?
COBOL developers find AI coding tools helpful for documentation and simple tasks but not yet a threat due to legacy system complexity and compliance constraints.
- Async Coding Agents "From Scratch"
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.