Autoresearch: The feedback loop behind self-improving agents

kept by eddie jul 02

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

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.
also on Cognition, Cursor, #ai-coding, #developer-tools
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.
also on Cognition, #ai-agents, #ai-coding, #software-engineering, #developer-tools
agent-skills/skills/autoreview/SKILL.md at main · openclaw/agent-skills
The piece defines a structured pre-commit code review skill for AI agents, specifying contracts, scope governance, and engine isolation across multiple review engines including Codex, Claude, and others.
also on pi, Cursor, #ai-coding, #software-engineering, #developer-tools
Building Pi With Pi
LLM-generated slop in issue trackers and code contributions harms open-source maintenance, forcing maintainers to resist local workarounds that undermine global invariants.
also on pi, #ai-agents, #open-source, #ai-coding, #software-engineering, #developer-tools
SpaceX says it has agreement to acquire Cursor for $60B
SpaceX has a potential deal to acquire AI coding startup Cursor for $60 billion or pay $10 billion for collaboration, sparking debate on valuation and strategy.
also on xAI, Cursor, #ai-coding, #developer-tools