AI · Article
AI can write code in an hour, but reviewing it still takes half a day
요즘IT ·

At a glance
At Japanese large companies, an AI coding tool turns a functional spec into implementation and test code in about an hour. Reviewing and fixing that output still takes more than half a day.
Key points
- The AI quickly drafts the implementation and unit tests (automatic code checks) from the spec.
- The AI sometimes assumed access it did not have or changed parts of the project that were not needed.
- If the spec itself is wrong, the code and tests can both be wrong, so people must check the source document separately.
- So the author now pays more attention to what files the AI reads and how far its task reaches.
Why it matters
The faster AI writes code, the more important it becomes for people to judge whether the results are correct.
Original source
일본 개발 현장에서 달라진 것: 구현은 단 1시간, 검토는 반나절
요즘IT · Nov 11, 14:00 KST
Read on 요즘IT ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to 요즘IT.
GitHub Copilot · Ranking and more news
More from this field
- Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST - OpenAI Shows How to Claim a Shopify Store in ChatGPT
This video shows how to claim your business in ChatGPT by connecting your Shopify store. You can start in Business Hub or the Shopify App Store. After connecting, you can manage your business information to control how your store appears in ChatGPT.
OpenAI 공식 YouTube · Nov 21, 05:48 KST