Each Sunday, NPR host Will Shortz, The New York Occasions’ crossword puzzle guru, will get to quiz 1000’s of listeners in a long-running section referred to as the Sunday Puzzle. Whereas written to be solvable with out too a lot foreknowledge, the brainteasers are normally difficult even for expert contestants.
That’s why some specialists suppose they’re a promising strategy to check the boundaries of AI’s problem-solving talents.
In a latest examine, a staff of researchers hailing from Wellesley School, Oberlin School, the College of Texas at Austin, Northeastern College, Charles College, and startup Cursor created an AI benchmark utilizing riddles from Sunday Puzzle episodes. The staff says their check uncovered stunning insights, like that reasoning fashions — OpenAI’s o1, amongst others — typically “quit” and supply solutions they know aren’t right.
“We needed to develop a benchmark with issues that people can perceive with solely basic information,” Arjun Guha, a pc science school member at Northeastern and one of many co-authors on the examine, instructed TechCrunch.
The AI trade is in a little bit of a benchmarking quandary in the intervening time. A lot of the checks generally used to guage AI fashions probe for abilities, like competency on PhD-level math and science questions, that aren’t related to the common person. In the meantime, many benchmarks — even benchmarks launched comparatively not too long ago — are rapidly approaching the saturation level.
The benefits of a public radio quiz recreation just like the Sunday Puzzle is that it doesn’t check for esoteric information, and the challenges are phrased such that fashions can’t draw on “rote reminiscence” to resolve them, defined Guha.
“I feel what makes these issues exhausting is that it’s actually tough to make significant progress on an issue till you resolve it — that’s when all the things clicks collectively unexpectedly,” Guha stated. “That requires a mix of perception and a means of elimination.”
No benchmark is ideal, in fact. The Sunday Puzzle is U.S. centric and English solely. And since the quizzes are publicly out there, it’s potential that fashions skilled on them can “cheat” in a way, though Guha says he hasn’t seen proof of this.
“New questions are launched each week, and we are able to count on the most recent inquiries to be really unseen,” he added. “We intend to maintain the benchmark contemporary and monitor how mannequin efficiency modifications over time.”
On the researchers’ benchmark, which consists of round 600 Sunday Puzzle riddles, reasoning fashions equivalent to o1 and DeepSeek’s R1 far outperform the remainder. Reasoning fashions completely fact-check themselves earlier than giving out outcomes, which helps them keep away from among the pitfalls that usually journey up AI fashions. The trade-off is that reasoning fashions take just a little longer to reach at options — sometimes seconds to minutes longer.
A minimum of one mannequin, DeepSeek’s R1, offers options it is aware of to be incorrect for among the Sunday Puzzle questions. R1 will state verbatim “I quit,” adopted by an incorrect reply chosen seemingly at random — conduct this human can actually relate to.
The fashions make different weird selections, like giving a incorrect reply solely to instantly retract it, try to tease out a greater one, and fail once more. Additionally they get caught “considering” endlessly and provides nonsensical explanations for solutions, or they arrive at an accurate reply instantly however then go on to think about different solutions for no apparent motive.
“On exhausting issues, R1 actually says that it’s getting ‘pissed off,’” Guha stated. “It was humorous to see how a mannequin emulates what a human may say. It stays to be seen how ‘frustration’ in reasoning can have an effect on the standard of mannequin outcomes.”
The present best-performing mannequin on the benchmark is o1 with a rating of 59%, adopted by the not too long ago launched o3-mini set to excessive “reasoning effort” (47%). (R1 scored 35%.) As a subsequent step, the researchers plan to broaden their testing to further reasoning fashions, which they hope will assist to establish areas the place these fashions is perhaps enhanced.
“You don’t want a PhD to be good at reasoning, so it needs to be potential to design reasoning benchmarks that don’t require PhD-level information,” Guha stated. “A benchmark with broader entry permits a wider set of researchers to understand and analyze the outcomes, which can in flip result in higher options sooner or later. Moreover, as state-of-the-art fashions are more and more deployed in settings that have an effect on everybody, we imagine everybody ought to have the ability to intuit what these fashions are — and aren’t — able to.”
