Meta launches the biggest and best AI models it has ever built13m ago AMD puts 32,768 CPU cores in a rack built for AI agents31m ago Smug until weirdly silent: who told us to say “I am alive”?38m ago Anthropic's Claude AI submitted false murder tip to Philadelphia police38m ago How Anthropic’s Dynamic Workflows Coordinate Claude Agents41m ago Dell’s AI partner ecosystem adapts to Silicon Valley’s build-it-yourself buyers44m ago AWS Expands GPT-6 Access on Amazon Bedrock to Five Asia Pacific Regions47m ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape50m ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters52m ago Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy53m ago Microsoft Research Introduces StudentSim for AI Tutor Training54m ago Why Big Tech Is Borrowing Billions to Fund AI Spending58m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy1h ago Meta Unveils New Series of Advanced A.I. Models2h ago

Meta launches the biggest and best AI models it has ever built13m ago AMD puts 32,768 CPU cores in a rack built for AI agents31m ago Smug until weirdly silent: who told us to say “I am alive”?38m ago Anthropic's Claude AI submitted false murder tip to Philadelphia police38m ago How Anthropic’s Dynamic Workflows Coordinate Claude Agents41m ago Dell’s AI partner ecosystem adapts to Silicon Valley’s build-it-yourself buyers44m ago AWS Expands GPT-6 Access on Amazon Bedrock to Five Asia Pacific Regions47m ago Disney's new CTO tells staff he 'won't pretend it will be easy' to win in the changing media landscape50m ago OpenAI Adds New Irish Roles in Boost to Firm’s EU Headquarters52m ago Manifold Steering from a Natural State is Effective and Generalizable, but Relies on Model Accuracy53m ago Microsoft Research Introduces StudentSim for AI Tutor Training54m ago Why Big Tech Is Borrowing Billions to Fund AI Spending58m ago Meet the Anthropic Engineer Keeping Its AI Agent Trustworthy1h ago Meta Unveils New Series of Advanced A.I. Models2h ago

Machine Learning5 min reading time

Vals, backed by Andreessen Horowitz, is looking to become the gold standard for AI benchmarking

TechCrunchPublished 23 days ago

Read the full article

Vals, a startup backed by Andreessen Horowitz, aims to modernize AI benchmarking by creating tests that better reflect current AI capabilities and prevent companies from gaming the system. Founded in 2024 by Rayan Krishnan, Vals keeps its test materials confidential to ensure fair evaluation beyond general knowledge assessments.

#ai-benchmarking #andreessen-horowitz #rayan-krishnan #vals

More in Machine Learning

Machine Learning

Meta Says New AI Model Is State-of-the-Art, Will Make Muse Agent Smarter

Covered by 2 sources2h ago

Machine Learning3 min read

Meta launches the biggest and best AI models it has ever built

Business Insider13m ago

Machine Learning3 min read

Microsoft launches a decision model built on Alibaba’s Qwen

The Next Web10h ago