AI safety
AssessTechniques
A field focused on reducing risks and harmful behavior from AI systems.
Why it's here
Placed in Assess: 4 article(s) of evidence from 1 source(s), led by funding news, with 0 in the last 30 days. Confidence 45%.
Evidence (4)
- 5OpenAI Blog·6/23/2026framework_updateOpenAI backs shared standards for advanced AI
OpenAI says it is helping develop shared standards for advanced AI, including evaluation frameworks and safety practices. The effort is being supported through the Appia Foundation and aims to strengthen global cooperation around responsible AI development.
- 5OpenAI Blog·4/6/2026fundingOpenAI launches Safety Fellowship pilot
OpenAI announced a pilot Safety Fellowship to support independent safety and alignment research. The program is also intended to help develop the next generation of talent in AI safety.
- 7OpenAI Blog·3/19/2026researchOpenAI monitors internal coding agents for misalignment
OpenAI describes how it uses chain-of-thought monitoring to study misalignment in internal coding agents. The approach analyzes real-world agent behavior to identify risks and improve AI safety safeguards.
- 7OpenAI Blog·2/19/2026fundingOpenAI funds independent AI alignment research
OpenAI is committing $7.5 million to The Alignment Project to support independent research on AI alignment. The funding is intended to strengthen global efforts focused on AGI safety and security risks.