Learn the fundamental pieces of code needed for building AI agents that can automate workflows, create original content, order pizza, and more.
We evaluated 9 closed-source and 1 open-source speech-to-text models on performance factors such as word error rate, words per minute, and cost.
Learn to safeguard AI training data from fraud with proven security frameworks. Read about threats in crowdsourcing and effective defense strategies.
Our research into chatbot performance using traditional ML shows how input filters increasingly need tailored training data to identify security risks.
This case study shows how compound adversarial attacks can be identified using unsupervised learning to overcome limited training data.
System prompt exfiltration is among the most alarming of LLM attacks. We propose a definition to make prompt exfiltration attacks easier to identify.
Input filters are a blue teaming operation and essential to building safe, secure LLMs.
Companies are eager to leverage the benefits generative AI (GenAI) offers. Implementing the technology, however, isn't a 'plug-and-play' process. Instead, it hinges on a critical task — fine-tuning a pretrained large language model (LLM) to be a specialist at your intended domain or application.
Learn how to adopt a mindset of continuous evaluation in generative AI, exploring popular benchmarks and AI red teaming methods.
These 3 conversational AI best practices will help you identify and develop new solutions, like natural language search tools, tailored to business goals.
Discover the processes involved in field operations testing for enhancing advanced driver assistance systems and key considerations for program success.
Learn how to automate the evaluation and categorization of LLM attack methods so your AI red team ensures good test coverage and finds vulnerabilities.
Get curated content delivered right to your inbox. No more searching. No more scrolling.
