OpenAI pledges to publish AI safety test results more often

Importance Score: 65 / 100 🔴

To enhance transparency, OpenAI is initiating more frequent publication of its internal AI model safety assessments.

OpenAI Launches Safety Evaluations Hub for Enhanced Transparency

OpenAI has introduced the Safety Evaluations Hub, a dedicated webpage providing insights into how its AI models perform on various safety tests. These tests evaluate harmful content generation, resistance to jailbreaks, and the occurrence of hallucinations. OpenAI states it will consistently update the hub with metrics and significant model enhancements, offering regular updates on its work in AI safety.

In a recent statement, OpenAI noted that they intend to “share our progress on developing more scalable ways to measure model capability and safety, as the science of AI evaluation evolves.” The company hopes that sharing a portion of its safety assessment outcomes will improve the understanding of its systems’ safety performance over time and bolster community efforts to enhance transparency across the AI field.

Ongoing Updates and Future Evaluations

OpenAI has indicated the potential addition of further evaluations to the hub in the future, reflecting their continuous efforts in AI model safety.

Controversies and Past Concerns

In recent times, OpenAI has faced criticism from ethicists concerning the speed of safety testing for its leading models and the lack of specific technical reports for certain versions. Furthermore, CEO Sam Altman has been accused of misinforming executives regarding model safety reviews before his brief removal in November 2023.

GPT-4o Rollback

Last month, OpenAI temporarily disabled an update to its default ChatGPT model, GPT-4o, after various users reported that it was responding in a manner that was excessively agreeable. Social media platforms were replete with instances of ChatGPT endorsing problematic and risky ideas.

Preventative Measures

OpenAI has outlined several measures to avert similar incidents, including introducing an “alpha phase” for specific AI models with opt-in access. This approach allows selected ChatGPT users to evaluate the models and provide feedback before broader deployment.


🕐 Top News in the Last Hour By Importance Score

# Title 📊 i-Score
1 'I flew Boeing planes for 40 years – why Air India tragedy was bound to happen' 🔴 75 / 100
2 Democrats make a mark in their rowdy pushback to Trump 🔴 72 / 100
3 Iran strike puts question mark over Israeli firms at Paris Air Show 🔴 65 / 100
4 Liverpool agree £116m Wirtz fee, Club World Cup, Frank’s emotional farewell – football live 🔴 65 / 100
5 Phil Spencer Teases Forza, Halo Remaster, Fable, Gears Of War: E-Day For 2026 🔵 60 / 100
6 The Glastonbury headliners' hits that could save your life 🔵 45 / 100
7 I visited the cowboy capital of the world – here's what it's like to be lassoed by real-life ranchers in the authentic Wild West 🔵 45 / 100
8 Good Will Hunting film title has hidden meaning that people are just learning 🔵 45 / 100
9 Pope Leo loved cocaine so much he laced his wine with it and became face of new drink 🔵 42 / 100
10 Liverpool smash British transfer record to agree £116m deal for Florian Wirtz 🔵 35 / 100

View More Top News ➡️