Each Sunday, NPR host Will Shortz, The New York Occasions’ crossword puzzle guru, will get to quiz hundreds of listeners in a long-running phase 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 consultants suppose they’re a promising solution to check the boundaries of AI’s problem-solving skills.
In a current research, a group of researchers hailing from Wellesley Faculty, Oberlin Faculty, the College of Texas at Austin, Northeastern College, Charles College, and startup Cursor created an AI benchmark utilizing riddles from Sunday Puzzle episodes. The group says their check uncovered stunning insights, like that reasoning fashions — OpenAI’s o1, amongst others — typically “quit” and supply solutions they know aren’t appropriate.
“We needed to develop a benchmark with issues that people can perceive with solely normal data,” Arjun Guha, a pc science school member at Northeastern and one of many co-authors on the research, informed iinfoai.
The AI business is in a little bit of a benchmarking quandary in the meanwhile. A lot of the exams generally used to guage AI fashions probe for abilities, like competency on PhD-level math and science questions, that aren’t related to the typical person. In the meantime, many benchmarks — even benchmarks launched comparatively just lately — 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 data, and the challenges are phrased such that fashions can’t draw on “rote reminiscence” to resolve them, defined Guha.
“I believe what makes these issues onerous is that it’s actually tough to make significant progress on an issue till you remedy it — that’s when all the pieces clicks collectively ,” Guha mentioned. “That requires a mixture 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 will count on the newest inquiries to be really unseen,” he added. “We intend to maintain the benchmark recent and observe 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 totally fact-check themselves earlier than giving out outcomes, which helps them keep away from a number of the pitfalls that usually journey up AI fashions. The trade-off is that reasoning fashions take somewhat longer to reach at options — sometimes seconds to minutes longer.
At the least one mannequin, DeepSeek’s R1, offers options it is aware of to be mistaken for a number of 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 mistaken reply solely to right away retract it, try to tease out a greater one, and fail once more. In addition they get caught “considering” perpetually and provides nonsensical explanations for solutions, or they arrive at an accurate reply instantly however then go on to contemplate different solutions for no apparent motive.
“On onerous issues, R1 actually says that it’s getting ‘annoyed,’” Guha mentioned. “It was humorous to see how a mannequin emulates what a human would possibly 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 just lately 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 determine areas the place these fashions is likely to be enhanced.
“You don’t want a PhD to be good at reasoning, so it ought to be potential to design reasoning benchmarks that don’t require PhD-level data,” Guha mentioned. “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 be capable of intuit what these fashions are — and aren’t — able to.”
