When AI writes the software, who verifies it?

kept by eddie mar 04

The Hacker News discussion argues that as AI writes more code, formal verification tools like Lean must scale to ensure correctness and trustworthiness.

One agent, every surface: how we built the Kiro agent harness - Kiro
Kiro unified its IDE, CLI, web, and iOS agent codebases into a single server‑side harness using ACP, enabling cross‑client sessions and shared features.
also on Cedar, #ai-agents, #ai-coding, #software-engineering, #developer-tools
Don't waste your back pressure ·
Providing AI agents with automated feedback loops (back pressure) enables them to self-correct on long-horizon tasks, increasing engineer leverage.
also on Lean, #ai-agents, #software-engineering, #developer-tools
When the Hard Part Stops Being Hard
Using an LLM to mechanize proofs in Lean cut months of work to weeks, showing that PL research can now be produced far faster, reshaping publication expectations.
also on Lean, #ai-coding, #software-engineering, #developer-tools
Thoughts on slowing the fuck down
Rapid adoption of AI coding agents in production codebases leads to compounding errors, complexity, and loss of maintainability; the author advocates for slowing down and maintaining human oversight.
also on AWS, #ai-agents, #ai-coding, #software-engineering, #developer-tools
The Software Development Lifecycle Is Dead
AI agents collapse the software development lifecycle into a tight loop of intent, build, observe, and repeat, making stages like requirements, testing, and code review obsolete.
also on AWS, #ai-agents, #ai-coding, #software-engineering, #developer-tools