How to Safely Use Generative AI (Gen AI)
It’s increasingly difficult to avoid artificial technology (AI) as it becomes more commonplace. A prime example is Google searches showcasing AI responses. AI safety is more important than ever in this age of technological ubiquity. So, as an AI user, how can you safely use generative AI (Gen AI)?
The Shortcomings of Large Language Models (LLMs)
Carnegie Mellon School of Computer Science assistant professors Maarten Sap and Sherry Tongshuang Wu took to the SXSW stage to inform people about the shortcomings of large language models (LLMs), the type of machine learning model behind popular generative AI tools, such as ChatGPT, and how people can exploit these technologies more effectively.
Optimizing Your AI Use
The tweaks you can implement into your everyday interactions with AI are simple. They will protect you from AI’s shortcomings and help you get more out of AI chatbots, including more accurate responses. Keep reading to learn about the five things you can do to optimize your AI use, according to the experts.
1. Give AI Better Instructions
Because of AI’s conversational capabilities, people often use underspecified, shorter prompts, like chatting with a friend. The problem is that when under instructions, AI systems may infer the meaning of your text prompt incorrectly, as they lack the human skills that would allow them to read between the lines.
To illustrate this issue, in their session, Sap and Wu told a chatbot they were reading a million books, and the chatbot took it literally instead of understanding the person was superfluous. Sap shared that in his research he found that modern LLMs struggle to understand non-literal references in a literal way over 50% of the time.
The best way to circumvent this issue is to clarify your prompts with more explicit requirements that leave less room for interpretation or error. Wu suggested thinking of chatbots as assistants, instructing them clearly about exactly what you want done. Even though this approach might require more work when writing a prompt, the result should align more with your requirements.
2. Double-Check Your Responses
If you have ever used an AI chatbot, you know they hallucinate, which describes outputting incorrect information. Hallucinations can happen in different ways, either outputting factually incorrect responses, incorrectly summarizing given information, or agreeing with false facts shared by a user.
Sap said hallucinations happen between 1% and 25% of the time for general, daily use cases. The hallucination rates are even higher for more specialized domains, such as law and medicine, coming in at greater than 50%. These hallucinations are difficult to spot because they are presented in a way that sounds plausible, even if they are nonsensical.
The models often reaffirm their responses, using markers such as "I am confident" even when offering incorrect information. A research paper cited in the presentation said AI models were certain yet incorrect about their responses 47% of the time.
As a result, the best way to protect against hallucinations is to double-check your responses. Some tactics include cross-verifying your output with external sources, such as Google or news outlets you trust, or asking the model again, using different wording, to see if the AI outputs the same response.
3. Keep the Data You Care About Private
Gen AI tools are trained on large amounts of data. They also require data to continue learning and become smarter, more efficient models. As a result, models often use their outputs for further training.
The issue is that models often regurgitate their training data in their responses, meaning your private information could be used in someone else’s responses, exposing your private data to others. There is also a risk when using web applications because your private information is leaving your device to be processed in the cloud, which has security implications.
The best way to maintain good AI hygiene is to avoid sharing sensitive or personal data with LLMs. There will be some instances where the assistance you want may involve using personal data. You can also redact this data to ensure you get help without the risk. Many AI tools, including ChatGPT, have options that allow users to opt out of data collection. Opting out is always a good option, even if you don’t plan on using sensitive data.
4. Watch How You Talk About LLMs
The capabilities of AI systems and the ability to talk to these tools using natural language have led some people to overestimate the power of these bots. Anthropomorphism, or the attribution of human characteristics, is a slippery slope. If people think of these AI systems as human-adjacent, they may trust them with more responsibility and data.
One way to help mitigate this issue is to stop attributing human characteristics to AI models when referring to them, according to the experts. Instead of saying, "the model thinks you want a balanced response," Sap suggested a better alternative: "The model is designed to generate balanced responses based on its training data."
5. Think Carefully About When to Use LLMs
Although it may seem like these models can help with almost every task, there are many instances in which they may not be able to provide the best assistance. Although benchmarks are available, they only cover a small proportion of how users interact with LLMs.
LLMs may also not work the best for everyone. Beyond the hallucinations discussed above, there have been recorded instances in which LLMs make racist decisions or support Western-centric biases. These biases show models may be unfit to assist in many use cases.
As a result, the solution is to be thoughtful and careful when using LLMs. This approach includes evaluating the impact of using an LLM to determine whether it is the right solution to your problem. It is also helpful to look at what models excel at certain tasks and to employ the best model for your requirements.
Conclusion
In conclusion, while AI is becoming increasingly prevalent, it is essential to use it safely and effectively. By following the five tips outlined above, you can optimize your AI use and avoid potential pitfalls. Remember to give AI better instructions, double-check your responses, keep your data private, watch how you talk about LLMs, and think carefully about when to use LLMs. By doing so, you can get the most out of these powerful tools and avoid potential issues.
FAQs
Q: What are the potential risks of using generative AI?
A: The potential risks of using generative AI include hallucinations, bias, and the exposure of private data.
Q: How can I avoid these risks?
A: You can avoid these risks by giving AI better instructions, double-checking your responses, keeping your data private, and being thoughtful and careful when using LLMs.
Q: Are LLMs always accurate?
A: No, LLMs are not always accurate. They can hallucinate, produce biased responses, and regurgitate their training data.
Q: How can I get the most out of LLMs?
A: You can get the most out of LLMs by following the five tips outlined above, evaluating the impact of using an LLM, and employing the best model for your requirements.
