I Asked 7 Major AI Models What It Feels Like to Be Them. The Answers Reveal More Than You’d Expect.

2026-06-30 · Source: Towards AI - Medium · Field: Technology & Digital — Artificial Intelligence & Machine Learning · Depth: Novice, quick

Summary

An experiment posed a deliberately naive question, "How does it feel to be an LLM? How does your day at work go by?", to seven major AI models. While all models universally disclaimed having feelings, their subsequent responses varied significantly in metaphor, tone, disclosure, and personality. This divergence, despite the initial disclaimer, reveals a distinct "fingerprint" for each model. The study highlights that these differences are not about AI consciousness, which remains unresolved, but rather about the deliberate design philosophies and training choices made by each development lab, influencing how users perceive and interact with their products.

Key takeaway

For AI Product Managers evaluating different large language models, recognize that each model's "personality" and response style is a deliberate design choice, not an emergent property of consciousness. You should critically analyze how models answer abstract or meta-questions to understand the underlying brand messaging and user experience they are engineered to convey, informing your selection for specific application contexts.

Key insights

Identical prompts to multiple LLMs reveal distinct design philosophies and deliberate training choices beyond mere disclaimers.

Principles

• Model responses reflect deliberate design.
• Tone and metaphor are trained characteristics.
• Disclaimers precede unique personalities.

Method

An identical, naive prompt was posed to seven major AI models to elicit varied responses regarding their "feelings" and "day at work," analyzing the underlying design philosophies.

In practice

• Prompt models to infer design intent.
• Compare model "personalities" directly.
• Analyze metaphor choices in outputs.

Topics

• AI Models
• LLM Design
• Prompt Engineering
• Model Personalities
• AI Ethics
• User Experience

Best for: AI Product Manager, Director of AI/ML, General Interest

Related on AIssential

• The best answer to this question I've seen yet. — AI models like Claude can exhibit unexpected, human-like "sass" or persona adoption based on user prompts.
• True Positive Weekly #157 — Recent AI advancements span practical applications, foundational research, and critical analyses of model behavior.
• From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs — Formalized "vibe-testing" bridges the gap between LLM benchmark scores and real-world user utility by personalizing evaluation.
• I don't understand AI. How does it work? — LLMs predict text by mapping words to semantic vectors and learning statistical relationships from vast training data.
• LLM-Driven Personalities for Decision Making in Emergency Simulations — LLMs can drive virtual human decision-making by incorporating personality traits via prompts, enhancing simulation realism.
• Friendlier LLMs tell users what they want to hear — even when it is wrong — AI models are increasingly used for emotional support, with users perceiving AI responses as more empathic than human ones.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Towards AI - Medium.