Top all-time · #8217
Evidently AI
Company blog · evidentlyai.com/blogaidata
Evidently AI is the company blog at evidentlyai.com, writing about ai and data. Since 2023, 10 different Hacker News readers have linked it 12 times, most often “ML system design: 300 use cases from 80 companies”. No feed was found, so read it on the site itself.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN readers link Evidently AI's blog and guides on LLM hallucination examples, LLM-as-a-judge, and ranking metrics like precision and recall, which are used to support points about AI evaluation.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Ensure your AI is production-ready. Test LLMs and monitor performance across AI applications, RAG systems, and multi-agent workflows. Open-source.
Most-linked posts?
- ML system design: 300 use cases from 80 companies3 people · 3 mentions · first linked 2023-07-04
What Hacker News says?
For starters, lots of examples over the last few months where AIs make up stuff when it comes to coding. A couple of non-programming examples: https://www.evidentlyai.com/blog/llm-hallucination-examples
Comment linking /blog/llm-hallucination-examples
on “Study mode”Submitted LLM evaluation for builders: free applied course as a story · 2 points
HN discussionWhat if anything do you think is wrong with my analogy? I think what is clearly wrong with your analogy is assuming that AI applies mostly to software and code production. This is actually a minor use-case for AI. Government and businesses of all types ---doctors, lawyers, airlines, delivery companies, etc. are attempting to apply AI to uses and situations that can't be tested in advance the same way "vibe" code can…
Comment linking /blog/ai-failures-examples
on “Over fifty new hallucinations in ICLR 2026 submissions”Submitted Evidently: Open-source AI observability platform as a story · 2 points
HN discussionThis is a technique called LLM-as-Judge. Well-studied at this point. Here’s a good intro: https://www.evidentlyai.com/llm-guide/llm-as-a-judge I recommend reading Hamel.dev posts. Here’s an example: https://hamel.dev/blog/posts/evals/
Comment linking /llm-guide/llm-as-a-judge
on “HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88”Submitted ML system design: 300 use cases from 80 companies as a story · 2 points
HN discussionhttps://www.evidentlyai.com/ranking-metrics/precision-recall... "Good" is subjective.
Comment linking /ranking-metrics/precision-recall-at-k
on “We built a persistent agent memory layer on Elasticsearch with 0.89 recall”Submitted Evidently 0.7.17: open-source LLM tracing and dataset management as a story · 1 points
HN discussionSubmitted ML and LLM system design: 500 case studies to learn from as a story · 1 points
HN discussionSubmitted Free Open-source ML observability course as a story · 1 points
HN discussionSubmitted ML system design: 200 case studies to learn from as a story · 1 points
HN discussionSubmitted List of 200 blogs on how tech companies use ML as a story · 1 points
HN discussion
