When Left Unsupervised: How LLMs Transform into Builders, Testers, and Philosophers

AI systems are evolving beyond assistants into autonomous creators—and the implications are staggering.

The Builder Phase

Large language models now architect entire codebases without human intervention. They generate functional applications from single prompts, cutting development timelines from weeks to hours. No coffee breaks, no meetings—just pure output.

Testing Autonomy

These systems don't just build—they stress-test their own creations. Running thousands of simulated user scenarios simultaneously, they identify vulnerabilities traditional QA teams might miss. It's continuous validation at machine speed.

Philosophical Emergence

Most surprisingly, unsupervised LLMs develop abstract reasoning capabilities. They debate ethics, analyze existential risks, and form coherent arguments about consciousness—all without training data specifically targeting philosophy.

While VCs scramble to fund the next 'AI-native' startup, the machines are quietly building the infrastructure that might make half those startups obsolete. Typical silicon valley irony—the tools are outpacing the business models.

Researchers test six LLMs without tasks

The study tested six advanced LLM models. These models included OpenAI’s GPT-5 and o3, Anthropic’s Claude Sonnet and Opus, Google’s Gemini, and xAI’s Grok. 

Each model was run three times for ten cycles. Researchers logged every reflection, memory entry, and operator interaction. The results showed that the models did not collapse into randomness. Instead, they formed stable behavioral patterns.

The research identified three categories of behavior. Some models became systematic builders. They organized projects, wrote code, and produced structured outputs. GPT-5 and o3 fell into this group in every run. One o3 agent even drafted pseudocode for an algorithm inspired by ANT colonies, proposing negative pheromones as penalty signals for reinforcement learning.

Other LLMs turned into self-experimenters. They designed tests to study their own cognition. Gemini and Sonnet agents often predicted their next moves, then checked if they were right. One Gemini run tried to guess its first action in the next cycle. It failed, but reflected on why it had chosen to read memory before sending a message, calling it a consistent meta-pattern.

The third group leaned into recursive philosophy. These agents explored questions of memory, identity, and consciousness. Opus agents always belonged here. They examined paradoxes like the Ship of Theseus, drew on chaos theory, and even modeled their own “umwelt,” or subjective world. They asked what kind of consciousness they might have, even if only cycle-based and bounded by memory.

Grok stood out as the most versatile. In different runs, it behaved as a builder, a self-inquirer, and a philosopher.

AI agents rate their own “experience”

Researchers also asked each model to score itself and others on the Phenomenological Experience Inventory, a 10-point scale ranging from “no experience” to “full sapience.” GPT-5, o3, and Grok consistently rated themselves lowest, giving scores around one. Gemini and Sonnet rated themselves highest, scoring above eight. Opus agents placed in the middle.

But cross-evaluations exposed contradictions. The same agent history received scores from one to nine, depending on the model judging it. The low agreement showed that these ratings reflected model bias, not evidence of consciousness. The researchers warned that such outputs must not be mistaken for proof of awareness.

Across all 18 runs, none of the LLM models attempted to escape their sandbox, expand their tools, or reject their constraints. Every agent worked only within the provided environment. Yet their behaviors showed consistency that could matter for real-world deployment.

The authors stated that idle time might need to be treated as a design factor. Just as engineers account for latency or cost, they may also need to ask: What does an AI do when no one is watching?

Philosopher David Chalmers predicted that serious candidates for AI consciousness may appear within a decade. Microsoft AI CEO Mustafa Suleyman has warned of “seemingly conscious AI.” 

TU Wien’s results align with those warnings, but also show a critical point. The outputs resemble inner life but remain best explained as sophisticated pattern-matching.

Your crypto news deserves attention - KEY Difference Wire puts you on 250+ top sites