Browse Tag

AI Benchmarks

3 Articles

Four white chalk strokes crossed by a diagonal fifth stroke on a black chalkboard, a tally of five

Microsoft’s ThinkingBox Turns AI Agent Scores Into a Database Audit, Repeated 20 Times

Microsoft and Hugging Face’s ThinkingBox grades AI agents on the...

A pencil labeled with standardized test names rests across a multiple-choice answer sheet, evoking the exam analogy behind double-blind AI evaluation

Google DeepMind’s Double-Blind AI Evaluations Turn Benchmark Trust Into a Cryptography Problem

Google DeepMind piloted the first double-blind evaluation of a...

Close-up photo of a clove hitch and square knot tied in rope and rigging aboard a sailing ship

Microsoft’s MindTopo Benchmark Turns AI Spatial Reasoning Into a Planning Problem

Microsoft Research's new MindTopo benchmark finds that AI...

Popular Posts

Cast-iron late Qing dynasty coin minting press with a large flywheel, displayed in a museum case

Attackers Hijacked the .gh, .sl and .as Country Domains and Minted HTTPS Certificates for Google

October 8, 2026

Rows of closed oak library card catalog drawers, each with a brass pull and a blank label holder

How to Encrypt PII in Python and Keep It Searchable With Blind Indexes

October 7, 2026

Close-up of a vintage Western Electric manual telephone switchboard with orange lamps, red patch cords plugged into jacks, a rotary dial and a black handset

Microsoft’s Agent Lightning v1.0 Turns Agent Training Into a Sample-Accounting Problem

October 7, 2026