Photo by Editor
# Introduction
Although large language models (LLMs) are often used for box roles, such as writing “email messages” or “working as advanced search engines”, they have many hidden strengths. It's just a matter of uncovering their hidden creative power to solve problems and extending them into less explored areas.
If you are interested in finding new examples of such unusual things to do with LLMs, this article lists and exemplifies seven of them, going beyond the usual conversation and discussions.
# 1. Playing Devil's Advocate for Decisions
AI chat systems are carefully trained to adapt to the end user, no matter what – unless told otherwise. The next time you need honest guidance in making decisions, instead of seeking validation, ask the AI to systematically challenge and dispel your ideas when needed, and test your thinking. For example, look at this sample prompt:
“Act as a cruel but reasonable critic. Review this project proposal and identify the top three hidden dangers or logical fallacies that I overlooked.”
# 2. Decryption of Arcane Technical Errors
This use case involves providing LLM with something like a private log file or raw stack trace, and asking it to convert this “machine generated frustration ball” into a natural language, step-by-step manual to fix the problem. A quick template like this (where you can paste the actual error log, instead of the part between the square brackets) can do the job nicely:
“I get this vague system error:
[paste error]Explain exactly which line is failing in plain English and give instructions to fix it.”
# 3. Navigating the Secret Language of Contracts and Law
Not sure what to sign in the rental agreement, and not willing to expend the energy required to wade through those endless, vague pages full of clauses? How about running it through an LLM – self-contained, for privacy reasons – and asking it to spot red flags?
“Analyze this rental agreement. Highlight any unusual termination clauses, hidden fees, or unusual liability shifts that someone could easily miss.”
# 4. Imitation of Historical Figures or Professional People
This is about encouraging the LLM to emulate a special communication style or philosophical framework associated with a historical figure, thus breaking away from conventional business thinking.
“Explore my modern social media strategy as if you were an advertising executive from 1960s Madison Avenue. Focus on emotional appeal and branding.”
# 5. Automating “Rubber Ducking” of Complex Logic
This is very useful in enabling the LLM to identify and indicate missing steps in a complex workflow or complex logic puzzle. Describe a complex workflow or puzzle in a model in an effort to test whether your mind map matches reality well. Take this template for information:
“I'm trying to build an automated workflow that starts based on these three specific scenarios:
[list conditions]Where is the logical gap in this sequence?”
# 6. Creating Your Own Personalized Skills Guide
Use this information to create a practical syllabus that leaves behind what you already know and focuses specifically on your specific knowledge and skill gaps, as well as the series' educational objectives:
“I already understand basic Python, but I want to learn how to visualize data. Create a free, 14-day learning plan with daily exercises focused exclusively on Matplotlib.”
# 7. Combining Real-Time Cultural Contexts
This is very useful in the field of international relations in defining the tone, formality, and cultural etiquette of foreign communications:
“Translate this email from a new international client, but also explain the subtext, the legal standard used, and how I should respectfully format my response to comply with cultural business standards.”
# Wrapping up
These seven use cases only scratch the surface of what's possible if you go beyond treating LLMs as simple question-answering machines.
Whether you're stress-testing your thinking, writing a formal written document, or bridging a cultural divide, the common thread is intentionality — giving the model a role, a clear responsibility, and a tangible goal. When you enter your requests deliberately, that's when these tools prove to be real understanding partners rather than glorified search engines.
Iván Palomares Carrascosa is a leader, author, speaker, and consultant in AI, machine learning, deep learning and LLMs. He trains and guides others in using AI in the real world.
