Your job is to deliver code you have proven to work

kept by eddie dec 19, 25

Software engineers must prove code works through manual and automated testing, shifting accountability away from AI agents to the human submitting the PR.

Writing code is cheap now
The Hacker News discussion argues that while AI makes generating code cheap, writing good software remains expensive, and code is a liability rather than an asset.
also on LLM, Simon Willison, #ai-coding, #software-engineering, #developer-tools
LLM predictions for 2026, shared with Oxide and Friends
Simon Willison predicts LLMs will write undeniably good code in 2026, sandboxing will be solved, and a coding agent security disaster is imminent.
also on LLM, Simon Willison, #ai-coding, #software-engineering
AddyOsmani.com - Comprehension Debt — the hidden cost of AI generated code.
Excessive reliance on AI coding tools creates comprehension debt—a growing gap between code volume and human understanding—that erodes system knowledge and eventually must be paid with interest.
also on #code-review, Simon Willison, #ai-coding, #software-engineering, #developer-tools
Fragments: April 29
The post collects expert perspectives on AI-assisted development, emphasizing verification over generation, harness engineering, function structure, and the cultural divide between software thinking and human experience.
also on codex-cli, Simon Willison, Claude Code, #ai-coding, #software-engineering, #developer-tools
The Optimal Amount of Slop is Non-zero - Doug Slater
Doug Slater argues developers should match code-review rigor to risk, shipping unreviewed LLM code is acceptable only for limited-distribution, low-consequence software.
also on #code-review, Claude Code, #ai-coding, #software-engineering, #developer-tools