BlindBench
About
Public AI benchmarks leak into training data. So which model is actually good at your task? #NEARHackathon BlindBench: private evals that pay their authors. Secret test sets, scored inside NEAR AI Cloud enclaves, certified on @NEARProtocol. 🧵👇
Media
Played from X. Open the post (1:10) (opens in a new tab)
From the builder’s post on X. Images and video are streamed from X’s servers, not copied.
Links
- Launch post on X
- x.com/YFarmX/status/2120354840501272782?a=RP0tjMCuPt2Gnei6K6Y&s=20 (opens in a new tab)
- Repository
- Not supplied
- Hackathon listing
- nearhackathon.com#submissions (opens in a new tab)All submissions: the source has no per-project page
Discussion · 0 comments
Each comment is signed by its author on NEARChecking your wallet…
No comments yet. Start the discussion.
Comments are public rows on nearhunt.near under comment/e4224cb4…. Only the author can delete one, because only they can write their own row. NEAR Hunt hides a comment that breaks the comment policy.