This Tool Probes Frontier AI Models for Lapses in Intelligence

This Tool Probes Frontier AI Models for Lapses in Intelligence
A new platform from data training company Scale AI will let artificial intelligence developers find their models’ weak spots.
Read more at Wired
Save Story

Topics in this Story

Related Stories

Gladia launches Solaria as AI-based multi-lingual speech recognition model for speech-to-text transcription

Gladia launches Solaria as AI-based multi-lingual speech recognition model for speech-to-text transcription

VentureBeat · 4d

Microsoft AI chief Suleyman sees advantage in building models ‘3 or 6 months behind’

CNBC · 1d
Vibe coding at enterprise scale: AI tools now tackle the full development lifecycle

Vibe coding at enterprise scale: AI tools now tackle the full development lifecycle

VentureBeat · 1d
Genies unveils user-generated content tools that let anyone create custom AI avatars

Genies unveils user-generated content tools that let anyone create custom AI avatars

VentureBeat · 2d
The tool integration problem that’s holding back enterprise AI (and how CoTools solves it)

The tool integration problem that’s holding back enterprise AI (and how CoTools solves it)

VentureBeat · 3d

Meta debuts new Llama 4 models, but most powerful AI model is still to come

CNBC · 17h
Calling all fashion models … now AI is coming for you

Calling all fashion models … now AI is coming for you

The Guardian · 6d
AI for CPG Innovation: The Power of Agility

AI for CPG Innovation: The Power of Agility

Inc. · 4d

Amazon's Nova AI agent launch puts it up against rivals OpenAI, Anthropic

CNBC · 5d
OpenAI to release open-source model as AI economics force strategic shift

OpenAI to release open-source model as AI economics force strategic shift

VentureBeat · 5d

Anthropic announces updates on security safeguards for its AI models

CNBC · 5d
Beyond RAG: How Articul8’s supply chain models achieve 92% accuracy where general AI fails

Beyond RAG: How Articul8’s supply chain models achieve 92% accuracy where general AI fails

VentureBeat · 1d
Inside DOGE’s AI Push at the Department of Veterans Affairs

Inside DOGE’s AI Push at the Department of Veterans Affairs

Wired · 1d
He Made an AI Tool to Help With Coding Interviews. Then Columbia University Suspended Him

He Made an AI Tool to Help With Coding Interviews. Then Columbia University Suspended Him

Inc. · Mar. 28
AI lie detector: How HallOumi’s open-source approach to hallucination could unlock enterprise AI adoption

AI lie detector: How HallOumi’s open-source approach to hallucination could unlock enterprise AI adoption

VentureBeat · 2d
Gartner forecasts gen AI spending to hit $644B in 2025: What it means for enterprise IT leaders

Gartner forecasts gen AI spending to hit $644B in 2025: What it means for enterprise IT leaders

VentureBeat · 5d
An AI Outperformed Human Doctors in a New Clinical Study. And It’s Humble

An AI Outperformed Human Doctors in a New Clinical Study. And It’s Humble

Inc. · 1d
Look Again: That H&M Model Showing Off a New Look May Be a Digital Clone

Look Again: That H&M Model Showing Off a New Look May Be a Digital Clone

The New York Times · Mar. 29
Trump administration announces plans to build AI data centers on federal land

Trump administration announces plans to build AI data centers on federal land

The Hill · 2d

Soccer-LaLiga leads AI evolution with global outreach

Yahoo Sports · 3d
A new, enterprise-specific AI speech model is here: Jargonic from aiOla claims to best rivals at your business’s lingo

A new, enterprise-specific AI speech model is here: Jargonic from aiOla claims to best rivals at your business’s lingo

VentureBeat · 6d
Beyond generic benchmarks: How Yourbench lets enterprises evaluate AI models against actual data

Beyond generic benchmarks: How Yourbench lets enterprises evaluate AI models against actual data

VentureBeat · 3d

AI race gives Washington another reason to be tough on TikTok

Financial Times · 3d
How to use AI to get a job interview and nail it – along with the salary you deserve

How to use AI to get a job interview and nail it – along with the salary you deserve

The Guardian · 5d
Meta's head of AI research announces departure

Meta's head of AI research announces departure

NBC News · 4d
DOGE is using AI the wrong way

DOGE is using AI the wrong way

The Hill · 5d

UK tech scheme includes AI tool to mark homework as ministers weigh selling data

Financial Times · 6d
Google’s Gemini 2.5 Pro is the smartest model you’re not using – and 4 reasons it matters for enterprise AI

Google’s Gemini 2.5 Pro is the smartest model you’re not using – and 4 reasons it matters for enterprise AI

VentureBeat · Mar. 29

CoreWeave tests investor appetite for AI

Financial Times · 6d
AI companies are commiting mass theft and hiding behind the language of 'training'

AI companies are commiting mass theft and hiding behind the language of 'training'

The Hill · 23h
Deep tech diplomacy: A US-Israel model for the age of AI

Deep tech diplomacy: A US-Israel model for the age of AI

The Hill · 5d
Sam Altman Says OpenAI Will Release an ‘Open Weight’ AI Model This Summer

Sam Altman Says OpenAI Will Release an ‘Open Weight’ AI Model This Summer

Wired · 5d
Anthropic scientists expose how AI actually ‘thinks’ — and discover it secretly plans ahead and sometimes lies

Anthropic scientists expose how AI actually ‘thinks’ — and discover it secretly plans ahead and sometimes lies

VentureBeat · Mar. 27
Amazon's Nova AI agent launch puts it up against rivals OpenAI, Anthropic

Amazon's Nova AI agent launch puts it up against rivals OpenAI, Anthropic

NBC News · 5d

High school sports: Longtime Frontier League director and advocate Kowalick dies at 88

Yahoo Sports · 3d

Scientists deploy AI to better predict wildfires

Financial Times · 4d

AI chipmaker Cerebras announces CFIUS clearance, a key step toward IPO

CNBC · 5d
Meta's head of AI research stepping down

Meta's head of AI research stepping down

ABC News · 4d

More from Wired

Best Apple Desktop Computers (2025): iMac, Mac Mini, Mac Studio

Best Apple Desktop Computers (2025): iMac, Mac Mini, Mac Studio

Wired · 38m
6 Best MagSafe Phone Grips (2025), Tested and Reviewed

6 Best MagSafe Phone Grips (2025), Tested and Reviewed

Wired · 1h
Scientists Are Mapping the Boundaries of What Is Knowable and Unknowable

Scientists Are Mapping the Boundaries of What Is Knowable and Unknowable

Wired · 2h
How Nissan Hopes to Navigate Trump’s Tariffs and Make Its EVs Great Again

How Nissan Hopes to Navigate Trump’s Tariffs and Make Its EVs Great Again

Wired · 3h
DOGE Is Planning a Hackathon at the IRS. It Wants Easier Access to Taxpayer Data

DOGE Is Planning a Hackathon at the IRS. It Wants Easier Access to Taxpayer Data

Wired · 21h

More in Tech

Best Apple Desktop Computers (2025): iMac, Mac Mini, Mac Studio

Best Apple Desktop Computers (2025): iMac, Mac Mini, Mac Studio

Wired · 38m
6 Best MagSafe Phone Grips (2025), Tested and Reviewed

6 Best MagSafe Phone Grips (2025), Tested and Reviewed

Wired · 1h
Scientists Are Mapping the Boundaries of What Is Knowable and Unknowable

Scientists Are Mapping the Boundaries of What Is Knowable and Unknowable

Wired · 2h
How Nissan Hopes to Navigate Trump’s Tariffs and Make Its EVs Great Again

How Nissan Hopes to Navigate Trump’s Tariffs and Make Its EVs Great Again

Wired · 3h
Can Using the Light Phone III Help Cure ‘Brain Rot’?

Can Using the Light Phone III Help Cure ‘Brain Rot’?

The New York Times · 4h