Programming for Prompt Engineering - 2024 entry

Prompt engineering is the art and science of interacting with large language models. These models are increasingly important in computer science and is being rolled out into applications. In this module you will program in Python to access both public large language modules, such as GPT-4, and local language models. To undertake this module you need to have some experience of using language models (through a chat interface) and of basic programming.

This model aims to give you skills to programmatically access the contents of large language models, using the Python language. This will allow you to batch process texts and/or images to undertake tasks across a range of applications. These might include, for example, sentiment analysis, text/image classification, text summarisation. It also allows you to undertake studies of language models by probing their behaviours in an experimental manner.hat do lecturers hope to cover in this module in terms of knowledge and learning opportunities for the students? Include details of research-enriched learning/ teaching and links to employment.

On successful completion of this module you should be able to:

Module Specific Skills and Knowledge

Discipline Specific Skills and Knowledge

Personal and Key Transferable / Employment Skills and Knowledge

The syllabus includes:

• The history of AI, ML and language models, putting them in context
• The technology of language models
• Programming techniques to access language models
• Legal and ethical issues of applications built with language models

Deferral – if you have been deferred for any assessment you will be expected to submit the relevant assessment. The mark given for a re-assessment taken as a result of deferral will not be capped and will be treated as it would be if it were your first attempt at the assessment.

Referral – if you have failed the module overall (i.e. a final overall module mark of less than 40%) you will be expected to submit the relevant assessment. The mark given for a re-assessment taken as a result of referral will be capped at 40%

Basic reading:

• Subject too new currently for a good textbook to be published.

Web based and Electronic Resources:

• “Demystifying Application Programming Interfaces (APIs): Unlocking the Power of Large Language Models and Other Web-based AI Services in Social Work Research” Perron et al. https://arxiv.org/abs/2410.20211

Other Resources:

• https://platform.openai.com/docs/api-reference/introduction
• ChatGPT system: https://openai.com/

Reading list for this module: