← 記事一覧に戻る
大規模言語モデルAIコーディング

Developers discover AI coding assistants struggle with messy legacy codebases — context limits force skilled engineers to supervise every suggestion

Hacker News · 2026年4月24日

AI要約

  • •A software developer with 20+ years of experience at a medical-device company tested Claude (an AI coding assistant) on their 20-year-old codebase and found it fails repeatedly because the AI cannot retain context of the entire system across work sessions — it generates code bloat and contradicts existing patterns without understanding the bigger picture.
  • •The core limitation: AI assistants like Claude are trained on clean, well-documented code examples, but real-world systems at established companies mix multiple coding styles, old design patterns, and undocumented decisions accumulated over decades. When the AI sees only a fragment of code in isolation, it makes suggestions that conflict with the system's hidden rules.
  • •For developers working in regulated industries (healthcare, finance, manufacturing), this means AI cannot yet be a solo tool — a human expert must review every suggestion to catch errors that could break critical systems. This flips the productivity promise: instead of AI reducing work, it currently adds review overhead unless the developer already knows the entire codebase by heart.
元記事を読む

関連記事

Coregit launches versioned filesystem for AI agents with 3.6× faster performance than GitHub
大規模言語モデル

Coregit launches versioned filesystem for AI agents with 3.6× faster performance than GitHub

Hacker News·2026年4月29日
大規模言語モデルAIコーディング

Ask HN: How do you differentiate with AI coding interviews?

Hacker News·2026年4月29日
Q is a slim LLM CLI tool that runs in the terminal, asking questions and debugging errors with session context from a single shell script.
大規模言語モデル

Q is a slim LLM CLI tool that runs in the terminal, asking questions and debugging errors with session context from a single shell script.

Hacker News·2026年4月29日
Mistral AI releases Workflows in public preview, a durable orchestration layer for enterprise AI built on Temporal.
大規模言語モデル

Mistral AI releases Workflows in public preview, a durable orchestration layer for enterprise AI built on Temporal.

Hacker News·2026年4月29日
大規模言語モデル

OpenAI's system prompt bans goblins, raccoons, and other creatures due to a GPT-5.4 bug that made the model obsessed with goblins.

Hacker News·2026年4月29日

AIニュースを毎日お届け

200以上のソースから厳選したAIニュースを毎日無料でお届けします。

無料で始める