Skip to main content

Prompt Engineering: Expert Tips for a variety of Platforms

 


Prompt engineering has become a crucial aspect of harnessing the full potential of AI language models. Both Google and Anthropic have recently released comprehensive guides to help users optimise their prompts for better interactions with their AI tools. What follows is a quick overview of tips drawn from these documents. And to think just a year ago there were countless YouTube videos that were promoting 'Prompt Engineering' as a job that could earn megabucks...

The main providers of these 'chatbots' will hopefully get rid of this problem, soon. Currently their interfaces are akin to 1970's command lines, we've seen a regression in UI. Constructing complex prompts should be relegated to Linux lovers. Just a word of caution, even excellent prompts don't stop LLM 'hallucinations'. They can be mitigated against by supplementing a LLM with a RAG, and perhaps by 'Memory Tuning' as suggested by Lamini (I've not tested this approach yet).  

In the meantime, here's how to cope with retro interfaces.

Clear and Direct Instructions

One of the most critical aspects of prompt engineering is to provide clear and direct instructions. This ensures that the AI model understands the task at hand and can generate relevant and coherent responses. For instance, when using Anthropic's Claude, it is essential to describe your task in detail, specifying exactly what you want the model to accomplish.


Separating Data from Instructions

Another key technique is to separate data from instructions. This helps the model to differentiate between the input data and the specific actions it needs to perform on that data. This approach is particularly useful when working with complex tasks that require multiple steps[4].


Using XML Tags

XML tags can be used to mark different parts of your prompt, which helps the AI model to recognize the structure and organization of the input. This is especially useful when dealing with tasks that require specific formatting or identification of certain elements within the text.

Including examples in your prompt can significantly improve the model's performance. The more examples you provide, the better the model can understand the task and generate relevant outputs. This approach is particularly effective when working with tasks that require specific formats or styles


Long Context

Using long context can be beneficial when working with tasks that require a deeper understanding of the input. Anthropic's Claude, for example, can process up to 100,000 tokens, allowing for more detailed and nuanced prompts. The average prompt is, apparently only 9 words long, 21 words is considered to be the minimum that's sufficient.


Avoiding Hallucinations

Hallucinations occur when the AI model generates information that is not present in the input data. To avoid this, it is essential to ensure that your prompts are specific and well-defined, and that you provide enough context for the model to understand the task accurately.


Building Complex Prompts

Building complex prompts involves combining multiple techniques and approaches to create a comprehensive and detailed prompt. This can be particularly useful when working with tasks that require multiple steps or involve complex data analysis.


Experimentation and Refining

Finally, it is crucial to experiment with different prompts and refine them based on the model's responses. This iterative process helps to identify the most effective prompts and optimize them for better performance.



Labels:

Comments

Post a Comment

Popular posts from this blog

The AI Dilemma and "Gollem-Class" AIs

From the Center for Humane Technology Tristan Harris and Aza Raskin discuss how existing A.I. capabilities already pose catastrophic risks to a functional society, how A.I. companies are caught in a race to deploy as quickly as possible without adequate safety measures, and what it would mean to upgrade our institutions to a post-A.I. world. This presentation is from a private gathering in San Francisco on March 9th with leading technologists and decision-makers with the ability to influence the future of large-language model A.I.s. This presentation was given before the launch of GPT-4. One of the more astute critics of the tech industry, Tristan Harris, who has recently given stark evidence to Congress. It is worth watching both of these videos, as the Congress address gives a context of PR industry and it's regular abuses. "If we understand the mechanisms and motives of the group mind, it is now possible to control and regiment the masses according to our will without their...
Post a Comment
Read more

CRM and AI?

Artificial intelligence (AI) can be used in a CRM system to enhance customer service, sales performance, and marketing strategies. Here are some examples of how AI can be applied in a CRM: - AI can enable natural language processing and voice input, such as Siri or Alexa, to allow a CRM system to answer customer queries, solve their problems, and even identify new opportunities for the sales team. Some AI-driven CRM systems can even multitask to handle all these functions and more. - AI can help with sales forecasting by analysing historical data, customer behaviour, and market trends. This can help the sales team make more accurate predictions for future sales figures and determine a success metric. - AI can assist with lead management by automating the process of qualifying and nurturing prospects. It can use chatbots and email bots to understand leads' needs and inform the sales team to improve their performance. With insights gained from these bots, companies can optimise their...
Post a Comment
Read more

Claude 3.5 Sonnet, literary analysis capabilities, an experiment

 There are those in the AI observer community that have been suggesting of late that 'AI has plateaued' which reveals, to me, a lack of understanding of how models develop. It's not iterative design but step changes we are witnessing. The differences between Claude 3 Sonnet and 3.5 Sonnet are stark.  One test I often carry out to asses the current capabilities of LLMs is to request a simple prompt to analyse an unpublished poem, commentating on the style and literary devices employed. The outputs have improved significantly over the 18 months I have employed this approach. This is my recent attempt. The poem is self written, self published (so not widely available) to ensure that it's unlikely to have found its way into the training data. For added context, implied in the text, this was written during a residency at a Museum and Art Gallery and came from a conversation with a member of staff about his late father. Calm is museum archival software. PROMPT. "analyse...
Post a Comment
Read more