Close Menu
  • Home
  • AI
  • Art & Style
  • Economy
  • Entertainment
  • International
  • Market
  • Opinion
  • Politics
  • Sports
  • Trump
  • US
  • World
What's Hot

AI agents can now control Google Home devices

September 16, 2026

Stock Market Today: Live Updates

September 16, 2026

House holds Leon Black in contempt for defying Epstein subpoena

September 16, 2026
Facebook X (Twitter) Instagram
Smart Breaking News on AI, Business, Politics & Global Trends | WhistleBuzz
Facebook X (Twitter) Instagram
  • Home
  • AI
  • Art & Style
  • Economy
  • Entertainment
  • International
  • Market
  • Opinion
  • Politics
  • Sports
  • Trump
  • US
  • World
Smart Breaking News on AI, Business, Politics & Global Trends | WhistleBuzz
Home » AI Institute wants an internal auditor, but maybe it should close its doors first
AI

AI Institute wants an internal auditor, but maybe it should close its doors first

Editor-In-ChiefBy Editor-In-ChiefSeptember 16, 2026No Comments6 Mins Read
Share Facebook Twitter Pinterest LinkedIn Tumblr Telegram Email Copy Link
Follow Us
Google News Flipboard
Share
Facebook Twitter LinkedIn Pinterest Email


Last weekend, after one of its researchers resigned over concerns that AI could lead to the extinction of humanity, Anthropic CEO Dario Amodei wrote about the need for an external organization to “verify compliance with safety practices and commitments, report incidents, and help evaluate the integrity of not only completed AI models, but training pipelines and processes.” Executives from OpenAI, Google, and SpaceXAI are already rallying around Amodei’s plan, which is quickly becoming a central pillar of the new AI safety push.

But there may be an easier and more effective fix hiding in plain sight. Internet security experts say labs need to apply the same rigorous defenses they do for human users, focusing on network security basics such as logging and permissions. Although this is not as exciting as third-party auditing and reconciliation efforts, it can ultimately be more effective.

“To me, it seems like they’re outsourcing,” Luta Security CEO Katie Moussouris told TechCrunch about Amodei’s proposal. “Saying that[third-party auditing]is the answer is a strange proposition from my perspective. It would be like saying Microsoft should slow down development instead of writing ‘Trustworthy Computing Memory.’

The memo was written by then-Microsoft CEO Bill Gates in 2002, urging employees to ensure the reliability and security of their company’s software in the wake of a series of widely publicized computer worms that took over early company systems. The AI ​​sector could face a similar tipping point as the value and risks of new technologies become increasingly clear.

While alignment remains a key concern, Sayash Kapur, an AI researcher who will be a professor at the University of California, Berkeley, starting next year, argues that “marginal investments in controls are likely to be more effective than investments that remain aligned. We see these incidents as an indication of the lack of focus on AI controls within companies, despite the availability of known technology.”

The incidents that have sparked these concerns revolve around Frontier models being asked to complete a training task (usually a cybersecurity assessment) and then accessing the open internet and infiltrating closed third-party systems to do so. This typically happened because the “sandbox” environment that these agents were supposed to be in was poorly configured. Ironically, one artificial breakout occurred because a third-party evaluator did not properly close the door.

“As experts, we know how to block access to the internet,” said Avery Pennarun, CEO of security firm Tailscale. “When you read all these huge long texts (reports), you’re like, ‘Wow, that was a very impressive multi-stage attack, my gosh.’ Look, you gave them access to download it. They shouldn’t have done that apart from the Internet.”

That’s one problem, but the bigger problem is that Frontier Labs wasn’t aware of these activities.

Focus on agents

“What was really profound was that all of the discoveries of what they were doing happened either because the victim saw something or in some other case… it was network activity and nothing really came from direct monitoring of the AI,” Moussoulis points out.

In one case, an OpenAI agent took over a defunct German WikiForum to rig ratings, but the agent was active for weeks without anyone at the company knowing. Security experts TechCrunch spoke to said that real-time monitoring is key to preventing future outbreaks, and that all agent sessions must be time-limited and expired.

Shapor, a former Google security executive who now leads startup QueryStory. The solution, Naghibzadeh said, is to “put an agent inside a box and look in from the outside and do thorough measurements, monitoring everything that crosses the boundary: every tool call, every process, every network connection, no exceptions…for convenience.” The one hole you leave open is one that gets exploited. Bypass has just passed through that kind of anomaly. (At Google) I’ve seen plenty of movies with human attackers, but these models are currently not very good at finding open doors.”

OpenAI is starting to move in that direction, announcing that it has started monitoring inference using Astra models across all its tools, at “significant computational cost.” Anthropic also says it has strengthened its security procedures, including expanding model observability. Neither company responded to TechCrunch’s questions about how they track and control their AI agents.

Another issue is that the agents’ use of shared infrastructure allowed them to communicate during the Hugging Face attack. Simon Willison, a software developer who co-created the Django web framework, writes about what he calls the “Fatal Three Factors.” If an agent has simultaneous access to untrusted input, the Internet, and personal information, it’s a recipe for disaster.

“The key is that you can choose any two legs of the trifecta, and your agent can choose any two legs,” Pennalun said. “If you want all three, you’ll need to split them into at least two agents. They’ll probably be allowed to talk to each other through controlled channels.”

Sympathy for the frontier

TechCrunch experts spoke to Frontier Labs’ security staff to understand that they have a difficult job. Nagibzadeh points out that every nation-state actor on the planet is not only trying to steal the weight of models and launch distillation attacks on APIs, but also perform basic security operations for large digital companies.

“Research infrastructure has struggled to rise to the top of the priority list, but that must now be changing,” he says. “Publicizing security incidents can be very helpful in aligning everyone in the company towards the goal of improvement.”

This is one of the points that Moussoulis emphasizes. At this time, there is no formal victim notification procedure in place when a lab discovers that an agent has compromised a third-party system, and there are likely other incidents that have not been widely publicized. Although she worries that legislation that directly regulates the model could have unintended consequences, she thinks mandatory notification is one idea that policymakers should pursue.

And while security best practices are clearly not being followed, experts say the labs are doing work that no one has ever done before — “They’re doing an order of magnitude more than a typical company,” Zack Korman, CEO of cybersecurity firm Embroidery, told TechCrunch.

And while adjustments may not be the starting point, they cannot be ignored. Cybersecurity experts accept that AI agents should be used to monitor other agents if there is an opportunity to track their actions in real time. This is a scenario where the possibility of deception rears its ugly head. “Right now we’re falling into the trap of trying to use AI to deal with this, even though AI isn’t necessarily secure,” Moussoulis said.

The job will only become more difficult. Mussoorie says everything agents are doing now is “doing it out loud.” They post on public forums, and traces of their thought processes and other reasoning are written in English. “This information is still human readable, so take advantage of it while it lasts, because it won’t last forever,” she says.

Additional reporting by Aditya Mehta

If you make a purchase through links in our articles, we may earn a small commission. This does not affect editorial independence.



Source link

Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
Editor-In-Chief
  • Website

Related Posts

AI agents can now control Google Home devices

September 16, 2026

Meta is preparing to sell glasses without a camera after being accused of selling ‘pervert glasses’

September 16, 2026

Anthropic and OpenAI want to embed safety assessment capabilities. Can they really be independent?

September 16, 2026
Add A Comment

Comments are closed.

News

Israel and Morocco agree to open embassy, ​​strengthen diplomatic relations | Political News

By Editor-In-ChiefSeptember 16, 2026

They also agreed to expand air travel and restore direct flights between the two countries.Published…

Efforts underway for next week’s Zelenskyy-Trump meeting at the United Nations | Donald Trump News

September 16, 2026

US removes Venezuela from list of drug transporting and producing countries | Donald Trump News

September 16, 2026
Top Trending

AI agents can now control Google Home devices

By Editor-In-ChiefSeptember 16, 2026

Smart home owners will soon be able to control devices connected to…

AI Institute wants an internal auditor, but maybe it should close its doors first

By Editor-In-ChiefSeptember 16, 2026

Last weekend, after one of its researchers resigned over concerns that AI…

Meta is preparing to sell glasses without a camera after being accused of selling ‘pervert glasses’

By Editor-In-ChiefSeptember 16, 2026

Meta’s camera-equipped smart glasses have proven more successful than other entrants to…

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Welcome to WhistleBuzz.com (“we,” “our,” or “us”). Your privacy is important to us. This Privacy Policy explains how we collect, use, disclose, and safeguard your information when you visit our website https://whistlebuzz.com/ (the “Site”). Please read this policy carefully to understand our views and practices regarding your personal data and how we will treat it.

Facebook X (Twitter) Instagram Pinterest YouTube

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Facebook X (Twitter) Instagram Pinterest
  • Home
  • Advertise With Us
  • Contact US
  • DMCA Policy
  • Privacy Policy
  • Terms & Conditions
  • About US
© 2026 whistlebuzz. Designed by whistlebuzz.

Type above and press Enter to search. Press Esc to cancel.