Frozen AI models act as time capsules that predict stock market returns better than the world's best financial analysts.
April 25, 2026
Original Paper
ChatGPT as a Time Capsule: The Limits of Price Discovery
SSRN · 6632823
The Takeaway
Large Language Models aggregate dispersed qualitative information that human investors struggle to synthesize. By looking at a fixed snapshot of an AI trained on past data, researchers can find hidden market signals. These signals were publicly available in text but remained invisible to the human eye. The model acts as a massive archive of human sentiment and knowledge that reveals future trends. This turns AI into a powerful tool for discovering the true value of assets.
From the abstract
Frozen large language model (LLM) checkpoints extract information from pre-cutoff public text that is associated with future fundamentals and equity returns beyond standard contemporaneous valuation measures. Because each frozen checkpoint has a fixed knowledge cutoff, it can be interpreted as a compressed representation of publicly available textual information at a given point in time. We treat twelve OpenAI snapshots spanning 2021-2025 as time-stamped summaries of the public textual record an