cd /news/ai-research/ask-hn-what-are-other-uncrackable-be… · home › topics › ai-research › article
[ARTICLE · art-121834] src=news.ycombinator.com ↗ pub= topic=ai-research verified=true sentiment=· neutral

Ask HN: What are other "uncrackable benchmarks"?

A Hacker News user asked the community for examples of private or 'hidden' AI benchmarks, citing their own unpublished benchmark based on a doctoral thesis and questioning whether discussing such benchmarks devalues them and whether a leak-proof test set can be created. The post received 3 points and 1 comment as of the time of writing.

read1 min views3 publishedSep 7, 2026

I have my own benchmark for AI just based off my Doctoral Thesis, which isn't public(university constraints). I am wondering if other people have other "hidden" benchmarks? I have a few I have made, and one wonder if talking about them devalues them, and two can a good test set be made that can't be leaked?

Comments URL: [https://news.ycombinator.com/item?id=49593357](https://news.ycombinator.com/item?id=49593357)

Points: 3
source & further reading
news.ycombinator.com — original article Ask HN: How has AI changed your QA validation workflows? Ask HN: How do you break AI agents out of the "apologize and repeat" loop Show HN: Building AI agents client-side JavaScript
── more in #ai-research 4 stories · sorted by recency
── more on @hacker news 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ask-hn-what-are-othe…] indexed:0 read:1min 2026-09-07 · —