I trust my coding agents with production secrets now

kept by eddie sep 07

The author trusts AI coding agents with full production secrets, arguing frontier models resist prompt injection and that access boosts productivity despite risks.

How to Do AI-Assisted Engineering - by Gregor Ojstersek
Engineers and leaders from 15 companies share structured workflows for AI-assisted coding, emphasizing design-first approaches, rigorous review, and context discipline over ad-hoc prompting.
also on OpenAI Codex, Claude, #ai-coding, #productivity, #developer-tools
Claude Code is about so much more than coding
Claude Code is a general-purpose AI agent that uses code to perform diverse knowledge work tasks, not just software development.
also on OpenAI Codex, Anthropic, #ai-agents, #ai-coding, #productivity
Claude's Voice Mode Just Got Smarter
Anthropic updated Claude’s voice mode to use Sonnet/Opus models, add Gmail/Slack context, and improve language support, while noting its turn‑based design limits naturalness.
also on Gmail, Claude, Anthropic, #productivity, #developer-tools
Software Too Cheap to Meter - by Steve Newman
AI coding agents like Claude Code now enable individuals to create personalized software for minor annoyances, such as a custom spam filter, at negligible cost.
also on Gmail, Claude, #ai-agents, #ai-coding, #developer-tools
Running Claude Code dangerously (safely)
Claude Code users discuss practical sandboxing strategies—VMs, containers, and firewalls—to safely run the agent with dangerous file-system permissions.
also on Docker, #security, Anthropic, #ai-coding, #developer-tools