Interpretability, meaning understanding the inner workings of AI systems, could be achieved before AI models reach an overwhelming level of power.
Unresolvable The public record could not settle it.
Prediction: Statements about events outside the person's control, checked once they fell due: did they come true?
Reasoning
Vague 'could be achieved' with no horizon or defined 'overwhelming power' threshold.
Cite this claim
Dario Amodei, “Interpretability, meaning understanding the inner workings of AI systems, could be achieved before AI models reach an overwhelming level of power.” (said 18 February 2025). Verdict: unresolvable. Reliability API, claim c_3630761e8138, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_3630761e8138
This claim is in dataset release v1.1.2, with the same verdict.
Reply to this claim
More prediction claims by Dario Amodei
-
Resolved true
“I would not be surprised at all if we hit ASL-3 next year.”
Dario Amodei said he would not be surprised at all if Anthropic's models hit ASL-3 in 2025.
-
Mostly true
“I don't think we have the level of autonomy yet to worry about some of the alignment stuff happening in two years, but it might not be very far behind that at all.”
-
Mostly false
“We believe AI for biology is on a similar exponential trend.”
-
Mostly true
“We're gonna be fine. The-- the impact of this designation is fairly small.”
-
Resolved false
“where AI is writing 90 percent of the code”
Within three to six months of March 2025, AI will be writing 90 percent of code.
Verdicts are made automatically; how verdicts are made.