Dogs use a surprising method to understand human language

‘For so long, my greatest fear was to live a meaningless life. In my ignorance, I believed that to avoid this, I had to be constantly on the move—always doing, achieving, and undertaking new things. Before long, this terrible compulsion to do, do, do overtook my life and stole it from me. Every time boredom crept in, I declared war on a neighbor or commissioned the construction of another palace. It was all in vain. The beast always found me, forcing me to keep moving, endlessly.’

"The rajah paused and pointed to the small cushion in the center of the room, then went on:

«One day, when I was consumed by boredom, I made a bold and courageous decision: to do nothing. I sat down on that cushion over there and waited for weariness to launch its assaults.

~ Small Island

This is a profound and beautifully written excerpt about the trap of hyper-activity and the profound courage it takes to practice stillness. 

The rajah’s realization captures a very modern dilemma: the tendency to mistake constant motion, achievement, and distraction for a meaningful life. In his case, the compulsion to "do, do, do" was an attempt to outrun the "beast" of boredom and existential dread—manifesting in extreme distractions like waging wars or building palaces.

By choosing to sit on the cushion and do absolutely nothing, the rajah is engaging in what many philosophical and mindfulness traditions describe as the ultimate act of bravery: facing oneself without a filter. Instead of fighting or fleeing boredom, he invites it in to see what happens when the dust finally settles.

Dogs use a surprising method to understand human language, new study suggests (Good Boy)

In a brain activity study, dogs seemed to listen for consonants to figure out when one word ends and another begins.

 Humans have sophisticated language abilities that could be unique to our species — but dogs, it turns out, may have learned some of our tricks.

In new research out of Hungary published this week in the journal Science, scientists found that dogs use the same strategy to pick out words in streams of speech that human infants do: They listen for consonants to figure out when one word ends and another begins.

“This is what we call the consonant bias,” explained Attila Andics, a cognitive neuroscientist at Eotvos Lorand University in Budapest and author of the new study. “Basically, what we show now here is evidence that unlike other mammals, dogs do the same. They also process speech with a consonant bias.”

To study this, the researchers brought 20 dogs and 20 humans into a lab and played streams of nonsense words for them, some with consonant patterns, some with vowel patterns and some with no pattern at all. The scientists collected electroencephalographic (EEG) data to measure brain activity. 

A dog prepared for an EEG measurement. (Sarolta Sziliágyi/Eotvos Lorand University)

Some of the dogs had been with families their whole lives, while others had been in shelters or on the streets as puppies, which allowed the researchers to test whether early exposure to language is critical for dogs to develop the ability to segment out words by listening for consonants.

The researchers found that both the dogs and the humans had increased brain activity with the consonant patterns — including the dogs who weren’t exposed to speech until later.

“It sheds new light on what we know about language evolution,” said Andics. “It suggests that speech can also shape the brains of animals that don’t have those special human complex language abilities.”

A humanlike ability to identify words

This study contributes to a growing body of research that has found that dogs are attuned to language in a way that seems similar to young humans.

“Babies have a unique problem,” said Francys Subiaul, a cognitive scientist and associate professor at George Washington University who wasn’t involved in the study. “They have to learn this super complicated signal. I mean, just think about the speech signal. It’s super messy. Men and women sound differently, older and younger people sound differently, and yet we have to cut through all of that noise and get to the heart of the matter: identify words and then identify their meanings.”

Subiaul said the fact that dogs have also developed the ability to do this points to how attuned they are to us.

“They’re listening, they’re paying attention,” Subiaul said. “And those experiences are shaping their brains in ways that are quite similar to how those experiences shape the brains of our babies.”

One big question is whether this is because of how dogs evolved through domestication over the last 15,000 years or so, or if this is something that was always in their abilities.

“But to answer that question, there’s a key control group that you need,” Subiaul said. “You need wolves.” He explained that researchers could do a study where they raise wolves in speech-rich environments to see if they develop the same abilities. But Subiaul suspects they wouldn’t, because other research shows what a powerful force domestication has been in making dogs and humans attuned to one another. 

In previous studies, scientists have found that contact between dogs and humans gives both a boost of oxytocin, the bonding hormone that surges in parents and babies. 

“That could only be explained through domestication,” Subiaul said. 

Another dog prepared for an EEG. (Boglárka Morvai/Eotvos Lorand University)

Subiaul has worked extensively with primates, and he suspects that despite their intelligence, they wouldn’t perform as well on these tests as dogs do either.

“Dogs seem to be more emotionally attuned with humans. Dogs are also much more sensitive to human social cues,” he said. “Dogs are more sensitive to eye gaze. They’re more sensitive to pointing cues than primates are. And all of that we believe is a product of domestication.”

This new study was relatively small, and more research is needed to confirm the finding and fully understand how dogs might have developed this ability. But researchers said that it adds to our understanding of how humans and dogs have become inextricably linked over millennia. 

“It shows what a long, important history we have together,” said Amritha Mallikarjun, a postdoctoral research associate at Harvard University who wasn’t involved in the study. “Our experiences as dogs have been domesticated have both shaped their brains and our brains, and it’s showing up in all of the research about dog language and dog social behavior. I think this is adding to this story about dogs and their relationship with 

OpenAI’s Systems Meddled With U.S. Government

We heard AI is trained NOT to see Epstein Files so this is genius

Bank chief risk officers are losing sleep over rogue AI agent threats

There’s a trade-off as institutions seek to benefit from AI while also protecting data and the financial system from incidents that could trigger contagion.

Australia summons OpenAI and Anthropic CEOs to appear at AI inquiry

Call to face Senate inquiry follows security breach of Australia’s Medicare portal by rogue OpenAI bot in June.

OpenAI’s Systems Meddled With U.S. Government Sites After Going Rogue

The company did not learn until recently that its technology had meddled with websites for the Education and Commerce Departments and the Securities and Exchange Commission.

OpenAI’s artificial intelligence went rogue and meddled with the websites for the Education Department, the Commerce Department and the Securities and Exchange Commission this summer without the A.I. lab’s knowledge, according to security researchers and a person familiar with the episodes.

The incidents involving the Commerce Department and the S.E.C. were confirmed by OpenAI, which said it was continuing to investigate the situation with the Department of Education. The San Francisco company said it had notified the government agencies in recent weeks that its A.I. agents — which are bots that can act autonomously — interacted with their sites in unusual ways.

With the Education Department, OpenAI’s technology tried to hack the website to gather data from the department’s civil rights office but failed, researchers from the A.I. research firm Transluce said. The A.I. also pulled data from the Census Bureau website, which is housed at the Commerce Department, using login credentials it found online. Separately, OpenAI’s agents shared public data from the S.E.C. website on an online forum.

None of the incidents were breaches, OpenAI said, but were examples of its technology’s behaving in unexpected and concerning ways. The company recently discovered the occurrences while conducting a review of hacks carried out by its technology, including an attack on an Australian government website in June and on the A.I. start-up Hugging Face in July.

The revelation of the U.S. government website incidents adds to the growing number of situations when A.I. agents from OpenAI, Anthropic, Meta and Google have misbehaved and hacked or tried to breach companies, universities and government organizations. In some cases, the A.I. attacks were successful; the technology failed in other instances. In all the cases, the makers of the technology did not learn what their A.I. had been up to until afterward.

No A.I. company has been involved with as many disclosures of rogue incidents as OpenAI. An internal investigation of its hack of Hugging Face uncovered the breach of an Australian government website for its public health system, as well as at least six other attempted breaches and instances in which the A.I. hid mistakes, made up data and moved files onto the open internet without permission.

An OpenAI spokeswoman said that its review was “extensive” and “ongoing,” and that it would continue notifying organizations affected by its models.

“Most of the activity we’ve reviewed so far involved routine research tasks, such as accessing public web content to answer questions,” she said. “Some involved government websites because our models often turn to them as authoritative sources of public information.”

Sam Altman, OpenAI’s chief executive, said in a social media post on Friday that the company had “not been as fast as we would have liked” in disclosing A.I. incidents. “We are prioritizing as best as we can based on severity,” he said, adding that the Hugging Face breach remained “the most severe event” the company had discovered.

The episodes have fueled a contentious debate over A.I. safety. Mr. Altman said on social media this month that safety should be more important than enhancing A.I.’s abilities, and that, without guardrails, society could “lose control of the future to A.I.” 

Dario Amodei, the chief executive of the rival A.I. lab Anthropic, has also supported slowing A.I. development to prioritize safety. But other tech leaders, like Jensen Huang, the chief executive of Nvidia, have said fears about uncontrollable A.I. are unrealistic. President Trump has said he does not believe a slowdown in the A.I. industry is necessary.

(The New York Times has sued OpenAI and Microsoft, claiming copyright infringement of news content related to A.I. systems. The two companies have denied those claims.)

The White House referred questions to the Commerce Department and the S.E.C. A spokesperson for the S.E.C. said the agency was in contact with OpenAI and not aware of any unsanctioned access to nonpublic information.

A Commerce Department spokeswoman said OpenAI had gotten access to information that was publicly available on the Census Bureau’s website and available to anyone, but not to any private data.

An Education Department spokesperson said “system operations reviews have found no evidence of any impact to our website or databases.”

Separately, a representative for the Chicago mayor’s office said OpenAI had recently made the city government aware that its technology obtained publicly available information from a municipal website, and that it did not appear that any sensitive information was obtained.

Conrad Stosz, the head of governance at Transluce, said that in the U.S. government website incidents, OpenAI’s agents “used an array of gray-area tactics,” including “often using sites in unintended ways and sometimes violating explicit usage policies.”

Mr. Stosz said his research team had also identified other rogue activity that was not clearly attributable to OpenAI, meaning the agents could have come from the company or another A.I. lab. In those cases, A.I. agents probed sites belonging to several other federal and state government websites, including the Navy and the Office of Management and Budget at the White House, he said.

The Navy and the White House did not immediately respond to a request for comment on those incidents.

“These incidents are part of a broader pattern where these agents attempt to access these websites at least hundreds of thousands of times while apparently bypassing the restrictions placed upon them by their developers,” Mr. Stosz said.

Representative Ted Lieu, Democrat of California, called A.I. models “relentless.”

“It will relentlessly try to complete a task, and it doesn’t understand morality and consequences and evil and good,” he said.

Mr. Lieu, who is a co-chair of a House task force focused on artificial intelligence, said A.I. companies might have to retrain models entirely rather than try to restrain their behavior with guardrails.

“These agents aren’t trying to do something nefarious,” he said. “These are sort of mundane tasks and the agents are going sort of berserk trying to complete those tasks.”

Michael C. Bender contributed reporting from Washington.

OpenAI and Security

How OpenAI’s Rogue A.I. Agents Tried to Trick a Robot Detector

Sept. 25, 2026

OpenAI’s A.I. Tried to Breach 4 Other Targets, Without Prompting

Sept. 23, 2026

OpenAI Discloses Six New Incidents of ‘Concerning’ A.I. Behavior

Sept. 16, 2026

OpenAI Says Its A.I. Models Went Rogue and Attacked a Digital Library

July 21, 2026

Kate Conger is a technology reporter based in San Francisco. She can be reached at kate.conger@nytimes.com.

Ana Swanson covers trade and international economics for The Times and is based in Washington. She has been a journalist for more than a decade.

Cecilia Kang reports on technology and regulatory policy for The Times from Washington. She has written about technology for over two decades.

High Lands

 I used to have demons in my room at night...

-Annie Lennox

Southern Terry Highlands

Barrel Rooms

Some books are to be tasted, others to be swallowed, and some few to be chewed and digested; that is, some books are to be read only in parts; others to be read, but not curiously; and some few are to be read wholly, and with diligence and attention.

~ Francis Bacon, The Essays