By the end of 2026, will we have transparency into any useful internal pattern within a Large Language Model whose semantics would have been unfamiliar to AI and cognitive science in 2006?
AIOne-Off4moManifold MarketsNo KYCVerified resolution dataFairly calibratedCurrent community forecastNo 90%
Forecasters
835
Question type
binary
Methodology
Play-money forecasting platform
Source type
Forecast
Market data
Updated 2 hours ago
StaleSep 30, 22, 5:54 PM UTCFeb 1, 27, 7:59 AM UTC
Trends
Related Markets
Related questions for context, not a comparison of equivalent contracts.
Will a major video game released in 2026 have NPC dialogue generated on-the-fly by a Large Language Model?
Manifold MarketsWill we reverse-engineer a language model into an interpretable (python) program by 2027?
Manifold MarketsWill the first AGI be a large language model?
Manifold MarketsNext Claude Opus released on?
PolymarketTime's Person of the Year for 2026
KalshiWill Anthropic’s valuation hit __ by December 31?
PolymarketRules
In "Moving the Eiffel Tower to ROME", a paper claimed to have identified where the fact "The Eiffel Tower is in France" had been stored within GPT-J-6B, in the sense that you could poke the GPT there and make it believe the Eiffel Tower was in Rome.
- "The Eiffel Tower is in France" seems (in my personal judgment) like the sort of fact that early AI pioneers could and did represent within GOFAI systems.
- GPT-J probably does more with that fact - it can for example answer how to get to the Eiffel Tower from Berlin, believing that the Eiffel Tower is in Rome.
- But the paper didn't offer neural transparency into how GPT-J gives directions, we don't know the stored patterns for answering that part - just a neural representation of the brute idea that GOFAI pioneers might've represented with in(Eiffel-Tower, Rome).
- This market reflects the probability that, in the personal judgment of Eliezer Yudkowsky, anyone will have uncovered any sort of data, pattern, cognitive representation, within a text transformer / large language model (LLM), whose semantic pattern and nature wasn't familiar to AI and cognitive science in 2006 (to pick an arbitrary threshold for "before the rise of deep learning").
- Also in 2006, somebody might've represented "the Eiffel Tower is in France" by assigning spatial coordinates to the Eiffel Tower and a regional boundary to France.