Urgent.News

What's breaking now, across thousands of outlets.

AI

Turning Japanese press releases (PR TIMES) into an LLM-ready dataset in 5 minutes

If you build anything that needs to understand the Japanese market — competitor monitoring, PR analytics, a RAG assistant for a sales team — you quickly run into a gap: most of the good structured news data is in English, and the Japanese sources that matter are not in your usual scraping toolkit. PR TIMES is the one to know. It is Japan's largest press-release distribution platform: more than…

PR TIMES, Japan's top press-release distribution platform, contains more than 100,000 company releases. It's the go-to source for Japanese companies looking to announce funding rounds, new store openings, product launches, and partnerships. Each release is consistent in format and includes a category, timestamp, and URL. The platform's data is clean and well-structured, making it ideal for feeding into large language models (LLMs) without needing to build a scraper first.

To use it, you can input keywords, company IDs, or release URLs. The free plan on Apify allows for about 5× faster and cheaper processing. Companies use this data for competitor monitoring, Japanese RAG corpora creation, PR analytics, and lead generation. Always attribute the source and summarize rather than republish the content.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Counting bugs is the hard part of comparing AI review tools

Model benchmarks for code review usually report the same two numbers: how many bugs the tool found, and how many of its comments were actually right. The part nobody can verify is the counting.

  • Verification process crucial in comparing AI review tools
  • Entelligence's benchmark uses double-judge validation method
  • Lack of disclosed labeling process makes precision numbers unreliable

Self-hosting AI code review is a model-placement decision, not a tool decision

When a team says it wants a self-hosted AI code reviewer, the real question is where the model runs, not which repo to clone. The tool is the easy part.

  • Self-hosted AI code reviewer decision hinges on model placement, not tool choice
  • PR-Agent repository on GitHub demonstrates model placement distinction
  • Options include hosted model + self-hosted app, local model + local app

More from Wednesday 16 September →