cryptonews

If you’ve worried that AI might take your job, deprive you of your livelihood, or maybe even replace your role in society, it probably feels good to see the latest AI tools fail spectacularly. If AI recommends glue as a pizza topping, then you’re safe for another day.

But the fact remains that AI already has definite advantages over even the most skilled humans, and knowing where these advantages arise—and where they don’t—will be key to adapting to the AI-infused workforce.

AI will often not be as effective as a human doing the same job. It won’t always know more or be more accurate. And it definitely won’t always be fairer or more reliable. But it may still be used whenever it has an advantage over humans in one of four dimensions: speed, scale, scope and sophistication. Understanding these dimensions is the key to understanding AI-human replacement.

Speed

First, speed. There are tasks that humans are perfectly good at but are not nearly as fast as AI. One example is restoring or upscaling images: taking pixelated, noisy or blurry images and making a crisper and higher-resolution version. Humans are good at this; given the right digital tools and enough time, they can fill in fine details. But they are too slow to efficiently process large images or videos.

AI models can do the job blazingly fast, a capability with important industrial applications. AI-based software is used to enhance satellite and remote sensing data, to compress video files, to make video games run better with cheaper hardware and less energy, to help robots make the right movements, and to model turbulence to help build better internal combustion engines.

Real-time performance matters in these cases, and the speed of AI is necessary to enable them.

Scale

The second dimension of AI’s advantage over humans is scale. AI will increasingly be used in tasks that humans can do well in one place at a time, but that AI can do in millions of places simultaneously. A familiar example is ad targeting and personalization. Human marketers can collect data and predict what types of people will respond to certain advertisements. This capability is important commercially; advertising is a trillion-dollar market globally.

AI models can do this for every single product, TV show, website and internet user. This is how the modern ad-tech industry works. Real-time bidding markets price the display ads that appear alongside the websites you visit, and advertisers use AI models to decide when they want to pay that price—thousands of times per second.

Scope

Next, scope. AI can be advantageous when it does more things than any one person could, even when a human might do better at any one of those tasks. Generative AI systems such as ChatGPT can engage in conversation on any topic, write an essay espousing any position, create poetry in any style and language, write computer code in any programming language, and more. These models may not be superior to skilled humans at any one of these things, but no single human could outperform top-tier generative models across them all.

It’s the combination of these competencies that generates value. Employers often struggle to find people with talents in disciplines such as software development and data science who also have strong prior knowledge of the employer’s domain. Organizations are likely to continue to rely on human specialists to write the best code and the best persuasive text, but they will increasingly be satisfied with AI when they just need a passable version of either.

Sophistication

Finally, sophistication. AIs can consider more factors in their decisions than humans can, and this can endow them with superhuman performance on specialized tasks. Computers have long been used to keep track of a multiplicity of factors that compound and interact in ways more complex than a human could trace. The 1990s chess-playing computer systems such as Deep Blue succeeded by thinking a dozen or more moves ahead.

Modern AI systems use a radically different approach: Deep learning systems built from many-layered neural networks take account of complex interactions—often many billions—among many factors. Neural networks now power the best chess-playing models and most other AI systems.

Chess is not the only domain where eschewing conventional rules and formal logic in favor of highly sophisticated and inscrutable systems has generated progress. The stunning advance of AlphaFold2, the AI model of structural biology whose creators Demis Hassabis and John Jumper were recognized with the Nobel Prize in chemistry in 2024, is another example.

This breakthrough replaced traditional physics-based systems for predicting how sequences of amino acids would fold into three-dimensional shapes with a 93 million-parameter model, even though it doesn’t account for physical laws. That lack of real-world grounding is not desirable: No one likes the enigmatic nature of these AI systems, and scientists are eager to understand better how they work.

But the sophistication of AI is providing value to scientists, and its use across scientific fields has grown exponentially in recent years.

Context matters

Those are the four dimensions where AI can excel over humans. Accuracy still matters. You wouldn’t want to use an AI that makes graphics look glitchy or targets ads randomly—yet accuracy isn’t the differentiator. The AI doesn’t need superhuman accuracy. It’s enough for AI to be merely good and fast, or adequate and scalable. Increasing scope often comes with an accuracy penalty, because AI can generalize poorly to truly novel tasks. The 4 S’s are sometimes at odds. With a given amount of computing power, you generally have to trade off scale for sophistication.

Even more interestingly, when an AI takes over a human task, the task can change. Sometimes the AI is just doing things differently. Other times, AI starts doing different things. These changes bring new opportunities and new risks.

For example, high-frequency trading isn’t just computers trading stocks faster; it’s a fundamentally different kind of trading that enables entirely new strategies, tactics and associated risks. Likewise, AI has developed more sophisticated strategies for the games of chess and Go. And the scale of AI chatbots has changed the nature of propaganda by allowing artificial voices to overwhelm human speech.

It is this “phase shift,” when changes in degree may transform into changes in kind, where AI’s impacts to society are likely to be most keenly felt. All of this points to the places that AI can have a positive impact. When a system has a bottleneck related to speed, scale, scope or sophistication, or when one of these factors poses a real barrier to being able to accomplish a goal, it makes sense to think about how AI could help.

Equally, when speed, scale, scope and sophistication are not primary barriers, it makes less sense to use AI. This is why AI auto-suggest features for short communications such as text messages can feel so annoying. They offer little speed advantage and no benefit from sophistication, while sacrificing the sincerity of human communication.

Many deployments of customer service chatbots also fail this test, which may explain their unpopularity. Companies invest in them because of their scalability, and yet the bots often become a barrier to support rather than a speedy or sophisticated problem solver.

Where the advantage lies

Keep this in mind when you encounter a new application for AI or consider AI as a replacement for or an augmentation to a human process. Looking for bottlenecks in speed, scale, scope and sophistication provides a framework for understanding where AI provides value, and equally where the unique capabilities of the human species give us an enduring advantage.

This essay was written with Nathan E. Sanders, and originally appeared in The Conversation.

This is a current list of where and when I am scheduled to speak:

• I’m speaking at the International Conference on Digital Trust, AI and the Future in Edinburgh, Scotland on Tuesday, June 24 at 4:00 PM.

The list is maintained on this page.

Video of the stubby squid (Rossia pacifica) from offshore Vancouver Island.

As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.

Paragon is a Israeli spyware company, increasingly in the news (now that NSO Group seems to be waning). “Graphite” is the name of their product. Citizen Lab caught them spying on multiple European journalists with a zero-click iOS exploit:

On April 29, 2025, a select group of iOS users were notified by Apple that they were targeted with advanced spyware. Among the group were two journalists that consented for the technical analysis of their cases. The key findings from our forensic analysis of their devices are summarized below:

• Our analysis finds forensic evidence confirming with high confidence that both a prominent European journalist (who requests anonymity), and Italian journalist Ciro Pellegrino, were targeted with Paragon’s Graphite mercenary spyware.
• We identify an indicator linking both cases to the same Paragon operator.
• Apple confirms to us that the zero-click attack deployed in these cases was mitigated as of iOS 18.3.1 and has assigned the vulnerability CVE-2025-43200.

Our analysis is ongoing.

The list of confirmed Italian cases is in the report’s appendix. Italy has recently admitted to using the spyware.

TecCrunch article.

This is news:

A data broker owned by the country’s major airlines, including Delta, American Airlines, and United, collected U.S. travellers’ domestic flight records, sold access to them to Customs and Border Protection (CBP), and then as part of the contract told CBP to not reveal where the data came from, according to internal CBP documents obtained by 404 Media. The data includes passenger names, their full flight itineraries, and financial details.

Another article.

Researchers have discovered a new way to covertly track Android users. Both Meta and Yandex were using it, but have suddenly stopped now that they have been caught.

The details are interesting, and worth reading in detail:

>Tracking code that Meta and Russia-based Yandex embed into millions of websites is de-anonymizing visitors by abusing legitimate Internet protocols, causing Chrome and other browsers to surreptitiously send unique identifiers to native apps installed on a device, researchers have discovered. Google says it’s investigating the abuse, which allows Meta and Yandex to convert ephemeral web identifiers into persistent mobile app user identities.

The covert tracking­implemented in the Meta Pixel and Yandex Metrica trackers­allows Meta and Yandex to bypass core security and privacy protections provided by both the Android operating system and browsers that run on it. Android sandboxing, for instance, isolates processes to prevent them from interacting with the OS and any other app installed on the device, cutting off access to sensitive data or privileged system resources. Defenses such as state partitioning and storage partitioning, which are built into all major browsers, store site cookies and other data associated with a website in containers that are unique to every top-level website domain to ensure they’re off-limits for every other site.

Washington Post article.

Southern New England is having the best squid run in years.

As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.

On Thursday I testified before the House Committee on Oversight and Government Reform at a hearing titled “The Federal Government in the Age of Artificial Intelligence.”

The other speakers mostly talked about how cool AI was—and sometimes about how cool their own company was—but I was asked by the Democrats to specifically talk about DOGE and the risks of exfiltrating our data from government agencies and feeding it into AIs.

My written testimony is here. Video of the hearing is here.

OpenAI just published its annual report on malicious uses of AI.

By using AI as a force multiplier for our expert investigative teams, in the three months since our last report we’ve been able to detect, disrupt and expose abusive activity including social engineering, cyber espionage, deceptive employment schemes, covert influence operations and scams.

These operations originated in many parts of the world, acted in many different ways, and focused on many different targets. A significant number appeared to originate in China: Four of the 10 cases in this report, spanning social engineering, covert influence operations and cyber threats, likely had a Chinese origin. But we’ve disrupted abuses from many other countries too: this report includes case studies of a likely task scam from Cambodia, comment spamming apparently from the Philippines, covert influence attempts potentially linked with Russia and Iran, and deceptive employment schemes.

Reports like these give a brief window into the ways AI is being used by malicious actors around the world. I say “brief” because last year the models weren’t good enough for these sorts of things, and next year the threat actors will run their AI models locally—and we won’t have this kind of visibility.

Wall Street Journal article (also here). Slashdot thread.

You can read the details of Operation Spiderweb elsewhere. What interests me are the implications for future warfare:

If the Ukrainians could sneak drones so close to major air bases in a police state such as Russia, what is to prevent the Chinese from doing the same with U.S. air bases? Or the Pakistanis with Indian air bases? Or the North Koreans with South Korean air bases? Militaries that thought they had secured their air bases with electrified fences and guard posts will now have to reckon with the threat from the skies posed by cheap, ubiquitous drones that cFan be easily modified for military use. This will necessitate a massive investment in counter-drone systems. Money spent on conventional manned weapons systems increasingly looks to be as wasted as spending on the cavalry in the 1930s.

There’s a balance between the cost of the thing, and the cost to destroy the thing, and that balance is changing dramatically. This isn’t new, of course. Here’s an article from last year about the cost of drones versus the cost of top-of-the-line fighter jets. If $35K in drones (117 drones times an estimated $300 per drone) can destroy $7B in Russian bombers and other long-range aircraft, why would anyone build more of those planes? And we can have this discussion about ships, or tanks, or pretty much every other military vehicle. And then we can add in drone-coordinating technologies like swarming.

Clearly we need more research on remotely and automatically disabling drones.

They’re interesting:

Tracked as CVE-2025-5054 and CVE-2025-4598, both vulnerabilities are race condition bugs that could enable a local attacker to obtain access to access sensitive information. Tools like Apport and systemd-coredump are designed to handle crash reporting and core dumps in Linux systems.

[…]

“This means that if a local attacker manages to induce a crash in a privileged process and quickly replaces it with another one with the same process ID that resides inside a mount and pid namespace, apport will attempt to forward the core dump (which might contain sensitive information belonging to the original, privileged process) into the namespace.”

Moderate severity, but definitely worth fixing.

Slashdot thread.

A new Australian law requires larger companies to declare any ransomware payments they have made.