As AI models achieve previously defined benchmarks for intelligence (e.g., reasoning), their failure to generate transformative economic value reveals those benchmarks were insufficient. This justifies 'shifting the goalposts' for AGI. It is a rational response to realizing our understanding of intelligence was too narrow. Progress in impressiveness doesn't equate to progress in usefulness.

When AI models achieve superhuman performance on specific benchmarks like coding challenges, it doesn't solve real-world problems. This is because we implicitly optimize for the benchmark itself, creating "peaky" performance rather than broad, generalizable intelligence.

AI intelligence shouldn't be measured with a single metric like IQ. AIs exhibit "jagged intelligence," being superhuman in specific domains (e.g., mastering 200 languages) while simultaneously lacking basic capabilities like long-term planning, making them fundamentally unlike human minds.

Progress towards AGI is not a smooth climb. Models exhibit "spikiness"—they can perform at a world-class level on one narrow domain but degrade to a "bad high school student" with slight perturbations. This non-intuitive generalization makes their capabilities uneven and unpredictable.

Current AI models resemble a student who grinds 10,000 hours on a narrow task. They achieve superhuman performance on benchmarks but lack the broad, adaptable intelligence of someone with less specific training but better general reasoning. This explains the gap between eval scores and real-world utility.

The Stanford AI Index reveals a "jagged frontier" where advanced models achieve superhuman performance on complex tasks like the International Mathematical Olympiad, yet fail at simple, common-sense activities like reading an analog clock. This highlights their lack of real-world grounding and the need for more holistic "world models."

Demis Hassabis explains that current AI models have 'jagged intelligence'—performing at a PhD level on some tasks but failing at high-school level logic on others. He identifies this lack of consistency as a primary obstacle to achieving true Artificial General Intelligence (AGI).

Hinton dismisses the concept of AGI as a singular moment when AI becomes equal to humans. He argues intelligence is 'jagged'—AI is already superhuman in domains like general knowledge but subhuman in others. There won't be a moment of perfect parity across all tasks.

AI models exhibit a "jaggedness" where capabilities are not uniform. They perform at expert levels on verifiable, RL-tuned tasks but remain basic on subjective, unoptimized ones (like humor). This suggests intelligence isn't generalizing smoothly across all domains.