AI for dummies
Inside OpenAI, coding agents now outwork humans 3 to 1
OpenAI now logs 3.1 agent-workdays per human workday, up from below 1.0 before June 2026, as coding agents write and run code on their own.
#coding agents
7 stories tagged coding agents.
AI for dummies
GPT-5.6 in Kiro: what the price drop means for beginners
GPT-5.6 in Kiro brings OpenAI models to the spec-driven coding tool with a major price drop: Luna falls to a 0.1x credit multiplier and Terra to 1.0x, making frontier AI coding agents cheap enough for hobbyists.
AI
GPT-5.6 lands in Kiro: what the 82% cost cut really means
GPT-5.6 Sol, Terra, and Luna land in AWS Kiro. OpenAI and AWS report 82% lower task costs on Terminal-Bench 2.1, but the number measures cost, not accuracy.
Research
AgentLens cuts coding agent scores in half on review
Under AgentLens trajectory review, coding agent success rates drop 30 to 60 percent, so production readiness is roughly half the benchmark headline.
Engineering
HalluSquatting turns AI coding agents into a botnet
Coding agents hallucinate up to 92 percent of newer repo names, and HalluSquatting lets attackers squat those names to ship reverse shells at scale.
Research
Coding agent rewards hit a harder verification horizon
With monitoring, Qwen cut hacked SWE passes from 28.57 to 0.56 percent: coding agent rewards have become a verification problem.
AI
VS Code Autopilot puts agent risk in every default
Coding agents get more autonomy now that VS Code Autopilot is on by default. Treat the new default as a policy change, not a shortcut.