Model-driven Prompt Engineering
We propose a DSL for prompt engineering to define platform-independent prompts that can later be adapted to provide good quality outputs in any target AI system
We propose a DSL for prompt engineering to define platform-independent prompts that can later be adapted to provide good quality outputs in any target AI system
Large Language Models (LLMs) are being quickly integrated in a myriad of software applications. This may introduce a number of biases, such as gender, age or ethnicity, in the behavior of such applications. To face this challenge, we explore the automatic generation of tests to assess the potential biases of an LLM.
ChatGPT is not yet a reliable tool to perform modeling tasks but any LLM can be of invaluable help in many areas of MBSE, complementing the current work of software modelers.
What does the ideal low-code platform for AI-based software look like? In this post we give our wish list for a low-code platform for smart software development
ChatGPT will not replace programmers. Even less modelers. But it may actually replace code-generators and become a key component in model-driven and low-code development platforms.
We introduce a domain-specific language for modeling AI engineering processes. The DSL enables you to describe how teams are developing AI-based software. As such, the DSL helps to clarify the process, simplify onboarding of new members and enables the analysis and enactment of the process.
Recent Comments