Anthropic's test to hire engineers had this Claude 'problem', here's how the company solved it

Anthropic has been forced to redesign its engineering hiring test multiple times. The AI startup had to make this change ...
Frontiers

Automated versus human scoring of the Rey-Osterrieth Complex Figure Test: a rapid review

Introduction: Despite digital advances in healthcare, clinical neuropsychology has been slow to adopt automated assessment tools. Automated scoring of the Rey-Osterrieth Complex Figure Test (ROCFT) ...
Frontiers

LLMs achieve adult human performance on higher-order theory of mind tasks

We introduce a new benchmark, MoToMQA, to assess human and LLM ToM abilities at increasing orders. MoToMQA is based upon the format of the Imposing Memory Task (IMT), a well-validated psychological ...
IEEE

HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenario

Abstract: The increasing labor shortage and aging population underline the need for assistive robots to support human care recipients. To enable safe and responsive assistance, robots require accurate ...
Los Angeles Times

Letters to the Editor: Trying to judge human ability by test scores always will invite debate

This is read by an automated voice. Please report any issues or inconsistencies here. Readers challenge whether SAT scores predict success, citing a high scorer rejected by 16 universities who later ...
Business Insider

Elon Musk says Tesla is now testing driverless robotaxis, without a human safety monitor, on Austin's streets

Every time Lakshmi publishes a story, you’ll get an alert straight to your inbox! Enter your email By clicking “Sign up”, you agree to receive emails from ...
newtelegraphng

Aliko Dangote: Setting New Benchmark In Human Capital Development

Education remains the cornerstone of socio-economic progress, particularly in developing nations. It is a powerful catalyst for breaking the cycle of poverty, driving innovation, and promoting ...
SpaceNews

Benchmark demonstrates high-throughput ASCENT thruster in hotfire testing at Edwards Air Force Base

Benchmark Macaw ASCENT thruster during hotfire testing Benchmark’s 22-Newton Macaw ASCENT thruster during hotfire at the company’s propulsion test facility near Pleasanton, California. Credit: ...
TMCnet

Nexar Unveils Nexar Apex: The First Real-World AV Testing Standard, Powered by 10 Billion Miles of Human Driving Data

New standard establishes the industry's first human benchmark for AV safety and debuts a real-world, data-driven AV City Readiness Index for scaling autonomous fleets NEW YORK, Dec. 4, 2025 ...
Morningstar

Hack The Box Launches the World’s First AI Cyber Range to Benchmark AI Agents and Accelerate Human-AI Teaming Across Offensive and Defensive Cyber Operations

Hack The Box Launches the World’s First AI Cyber Range to Benchmark AI Agents and Accelerate Human-AI Teaming Across Offensive and Defensive Cyber Operations Hack The Box (HTB), the global leader in ...
Seeking Alpha

AIEQ: The Human Vs. AI Stock-Picking Test

The Amplify AI-Powered Equity ETF leverages IBM Watson and EquBot AI to pick stocks, aiming for faster, data-driven decisions than human managers. AIEQ has underperformed the S&P 500 since 2021, ...