How to use artificial intelligence in information searching

Definition of AI

Artificial intelligence is not a specific method of processing data, so it has been particularly difficult to find a definition that would satisfy everyone.

The main features that define AI are

• the ability to perform activities that are considered to require human intelligence
• the ability to act independently, autonomously
• the ability to interact with signals and data received from the environment and adapt its actions to them in relation to the system’s past operation and outputs (system learning)
• the objective to achieve goals and produce output requested by a human from the system in a way that optimises the results of achieving the objective.

Reference: Digital and Population Data Services Agency. (13.11.2023). Guide for service developers: Using AI responsibly. https://kehittajille.suomi.fi/guides/responsible-ai/introduction-to-data-ethics/learn-about-past-discourse

Picture: Geralt. (n.d.). Pixabay. https://pixabay.com/fi/illustrations/verkko-verkkoon-tietotekniikka-4861605/

What is AI not? Microsoft Copilot answers

1. AI is not intelligence—it is prediction: While AI systems can make accurate predictions based on data, it’s essential to recognize that this isn’t equivalent to human intelligence. For instance, large language models like ChatGPT can predict the next word in a sentence, but they lack the transferable intelligence that humans possess.

2. AI is not automation: Another misconception is equating AI with automation. Although both rely on data and aim to streamline convenience, they serve different purposes. AI involves complex tasks like reasoning, decision-making, and problem-solving, whereas automation focuses on repetitive tasks.

3. AI is not infallible: While AI systems can perform impressive tasks, they are not perfect. They can make mistakes, especially when faced with novel situations or incomplete data. It's essential to recognize their limitations and not blindly trust their outputs.

4. AI is not inherently unbiased: AI models learn from historical data, which can contain biases. If the training data is biased, the AI system may perpetuate those biases. Efforts are being made to create fairer and more unbiased AI, but it's an ongoing challenge.

5. AI is not creative in the same way humans are: While AI can generate content like poems, stories, or music, it lacks the depth of human creativity. AI generates based on patterns it has learned, whereas human creativity involves intuition, emotions, and unique perspectives

6. AI is not self-aware: Despite its impressive abilities, AI lacks consciousness or self-awareness. It doesn't understand its own existence or have desires, fears, or preferences. It's a tool created by humans, not a sentient being.

7. AI is not a replacement for human judgment: AI can assist decision-making, but it shouldn't replace human judgment entirely. Context, ethics, and empathy are essential aspects of decision-making that AI lacks.

Remember that AI is a powerful tool, but it's essential to use it wisely, understand its limitations, and complement it with human expertise.