Opening a new era in algorithmic developmentDeep DiveAlessandro Curioni and Jay Gambetta05 Aug 2025Computer Science
Debugging LLMs to improve their credibilityResearchKim Martineau30 Jul 2025AIExplainable AIGenerative AINatural Language ProcessingOpen SourceTrustworthy AITrustworthy Generation
How IBM’s Kush Varshney became the face of the modern ‘camera man’ Q & AKim Martineau21 Jul 2025AIGenerative AITrustworthy AI
IBM’s safety checkers top a new AI benchmarkNewsKim Martineau09 Apr 2025AIAI TransparencyFairness, Accountability, TransparencyGenerative AINatural Language Processing
Why we’re teaching LLMs to forget things ExplainerKim Martineau07 Oct 2024AIGenerative AINatural Language ProcessingTrustworthy AI
A toxic language filter built for speedNewsKim Martineau09 Sep 2024AIFoundation ModelsOpen SourceTrustworthy AI
What is red teaming for generative AI?ExplainerKim Martineau11 Apr 2024Adversarial Robustness and PrivacyAIAI TestingFairness, Accountability, TransparencyFoundation ModelsNatural Language ProcessingSecurityTrustworthy AI
The latest AI safety method is a throwback to our maritime pastResearchKim Martineau16 Nov 2023AIAI TransparencyExplainable AIFairness, Accountability, TransparencyGenerative AI
IBM Science for Social Good 2019 projects announcedNewsKush Varshney and Aleksandra Mojsilovic23 Jul 20194 minute readAIHybrid CloudImpact Science