Harvard researchers find AI coding agents shifted the bottleneck to code review

·Hacker News··

Harvard study: AI coding agents raised code output 30 percent; finished work did not measurably rise, and getting code through review took 49 percent longer.

Read full article →

Related Articles

Unauthenticated remote code execution in Nginx
speedping · Hacker News · 4h ago
Highly classified US national security communications network goes down
monkeydust · Hacker News · 1d ago
New Evidence Shows School Phone Bans Are Gradually Improving Test Scores
donohoe · Hacker News · 1d ago
Java4Shell: RCE in OpenJDK when processing Base64
werrett · Hacker News · 23h ago
U.S. AirForce is looking for old storage Media (CF or PC cards)
birdboat00 · Hacker News · 4h ago