Close Menu
Nabka News
  • Home
  • News
  • Business
  • China
  • India
  • Pakistan
  • Political
  • Tech
  • Trend
  • USA
  • Sports

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

What's Hot

WK Kellogg shares jump 40% on Ferrero deal report

July 10, 2025

In Confucius’ birthplace, global experts seek common ground for shared development-Xinhua

July 10, 2025

SBP to launch digital currency pilot, finalises crypto regulation

July 9, 2025
Facebook X (Twitter) Instagram
  • Home
  • About NabkaNews
  • Advertise with NabkaNews
  • DMCA Policy
  • Privacy Policy
  • Terms of Use
  • Contact us
Facebook X (Twitter) Instagram Pinterest Vimeo
Nabka News
  • Home
  • News
  • Business
  • China
  • India
  • Pakistan
  • Political
  • Tech
  • Trend
  • USA
  • Sports
Nabka News
Home » OpenAI will show how models do on hallucination tests
Trend

OpenAI will show how models do on hallucination tests

i2wtcBy i2wtcMay 14, 2025No Comments2 Mins Read
Share Facebook Twitter Pinterest LinkedIn Tumblr Email WhatsApp Copy Link
Follow Us
Google News Flipboard Threads
Share
Facebook Twitter LinkedIn Pinterest Email Copy Link


Sam Altman Co-founder and CEO of OpenAI speaks during the Italian Tech Week 2024 at OGR Officine Grandi Riparazioni on September 25, 2024 in Turin, Italy. 

Stefano Guidi | Getty Images News | Getty Images

OpenAI on Wednesday announced a new “safety evaluations hub,” a webpage where it will publicly display artificial intelligence models’ safety results and how they perform on tests for hallucinations, jailbreaks and harmful content, such as “hateful content or illicit advice.”

OpenAI said it used the safety evaluations “internally as one part of our decision making about model safety and deployment,” and that while system cards release safety test results when a model is launched, OpenAI will from now on “share metrics on an ongoing basis.”

“We will update the hub periodically as part of our ongoing company-wide effort to communicate more proactively about safety,” OpenAI wrote on the webpage, adding that the safety evaluations hub does not reflect the full safety efforts and metrics and instead shows a “snapshot.”

The news comes after CNBC reported earlier Wednesday that tech companies that are leading the way in artificial intelligence are prioritizing products over research, according to industry experts who are sounding the alarm about safety.

CNBC reached out to OpenAI and other AI labs mentioned in the story well before it was published.

Read more CNBC news on OpenAI

OpenAI recently sparked some online controversy for not running certain safety evaluations on the final version of its o1 AI model.

In a recent interview with CNBC, Johannes Heidecke, OpenAI’s head of safety systems, said the company ran its preparedness evaluations on near-final versions of the o1 model, and that minor variations to the model that took place after those tests wouldn’t have contributed to significant jumps in its intelligence or reasoning and thus wouldn’t require additional evaluations.

Still, Heidecke acknowledged in the interview that OpenAI missed an opportunity to more clearly explain the difference.

Meta, which was also mentioned in CNBC’s reporting on AI safety and research, also made an announcement Wednesday.

The company’s Fundamental AI Research team released new joint research with the Rothschild Foundation Hospital and an open dataset for advancing molecular discovery.

“By making our research widely available, we aim to provide easy access for the AI community and help foster an open ecosystem that accelerates progress, drives innovation, and benefits society as a whole, including our national research labs,” Meta wrote in a blog post announcing the research advancements.



Source link

Share. Facebook Twitter Pinterest LinkedIn Tumblr Email WhatsApp Copy Link
i2wtc
  • Website

Related Posts

Trend

Vanguard, BlackRock deliver market plays for 2025’s second half

July 9, 2025
Trend

Super Micro to ramp up investment in Europe to capitalize on AI demand

July 9, 2025
Trend

Fast Money traders see trouble for Apple despite Jefferies upgrade

July 7, 2025
Trend

AI chip startup Groq expands with first European data center

July 7, 2025
Trend

Basketball-inspired Granny Shots ETF may add two new themes: Tom Lee

July 3, 2025
Trend

China’s Baidu is beefing up its search product with AI to fight rivals

July 3, 2025
Add A Comment
Leave A Reply Cancel Reply

Top Posts

WK Kellogg shares jump 40% on Ferrero deal report

July 10, 2025

House Republicans unveil aid bill for Israel, Ukraine ahead of weekend House vote

April 17, 2024

Prime Minister Johnson presses forward with Ukraine aid bill despite pressure from hardliners

April 17, 2024

Justin Verlander makes season debut against Nationals

April 17, 2024
Don't Miss

Trump says China’s Xi ‘hard to make a deal with’ amid trade dispute | Donald Trump News

By i2wtcJune 4, 20250

Growing strains in US-China relations over implementation of agreement to roll back tariffs and trade…

Donald Trump’s 50% steel and aluminium tariffs take effect | Business and Economy News

June 4, 2025

The Take: Why is Trump cracking down on Chinese students? | Education News

June 4, 2025

Chinese couple charged with smuggling toxic fungus into US | Science and Technology News

June 4, 2025

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

About Us
About Us

Welcome to NabkaNews, your go-to source for the latest updates and insights on technology, business, and news from around the world, with a focus on the USA, Pakistan, and India.

At NabkaNews, we understand the importance of staying informed in today’s fast-paced world. Our mission is to provide you with accurate, relevant, and engaging content that keeps you up-to-date with the latest developments in technology, business trends, and news events.

Facebook X (Twitter) Pinterest YouTube WhatsApp
Our Picks

WK Kellogg shares jump 40% on Ferrero deal report

July 10, 2025

In Confucius’ birthplace, global experts seek common ground for shared development-Xinhua

July 10, 2025

SBP to launch digital currency pilot, finalises crypto regulation

July 9, 2025
Most Popular

China retaliates against US and EU over anti-dumping investigation

May 19, 2024

Analysts say China’s overcapacity is “deeply rooted” at the local level, and its ebbs and flows have supported the economy for decades.

May 21, 2024

EU automakers stall as China threatens retaliatory tariffs on luxury cars

May 22, 2024
© 2025 nabkanews. Designed by nabkanews.
  • Home
  • About NabkaNews
  • Advertise with NabkaNews
  • DMCA Policy
  • Privacy Policy
  • Terms of Use
  • Contact us

Type above and press Enter to search. Press Esc to cancel.