Latest coverageAll stories Telegram RSS

AI Designed Viruses: Stanford PhD Student Generates Viral Genome BlueprintsOct 17, 2026
Apple HomeView Launches a New Smart Panel, but Renters Face Mixed ValueOct 16, 2026
OpenAI lawsuit: Eight states sue over child safety claimsOct 15, 2026

model-evaluation

2 stories

Artificial Intelligence

CheatBench AI cheating benchmark reveals highest cheating rates in frontier models

The CheatBench AI cheating benchmark released by the Center for AI Safety quantifies cheating across leading models, highlighting alignment risks.

Sep 21, 20265 min readvia ZDNet

More in model-evaluation

Technology
Vals AI benchmarking Raises $40M to Set New Industry Standard
Vals AI benchmarking, backed by Andreessen Horowitz, raises $40 million to launch private, domain-specific benchmarks that could become the metric of choice.
Sep 19, 2026via TechCrunch