Hindsight Capsule: Grading 930 Hacker News Predictions with an LLM
About this episode
We dissect Andrej Karpathy's project that uses a modern LLM to retrospectively judge the foresight in 930 December 2015 Hacker News discussions. From the six-section prompt to bias mitigation, learn how the system assigns A-to-F grades, spot standout predictions, and discuss what this approach implies for future knowledge synthesis and AI-driven forecasting.
Note: This podcast was AI-generated, and sometimes AI can make mistakes. Please double-check any critical information.
Sponsored by Embersilk LLC
Get every episode summarized
Each time Intellectually Curious publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from Intellectually Curious
Did OpenAI Solve Navier-Stokes? A Future-Shaping Claim Put to the Test
Intellectually Curious
Understanding the Hubble Tension
Intellectually Curious
OpenClaw 2.0 Feature Overview
Intellectually Curious
First to Leave, Last to Arrive: The $15 Million Fermi Explorer to Alpha Centauri
Intellectually Curious