Feed aggregator

Article URL: https://arxiv.org/abs/2507.14415

Comments URL: https://news.ycombinator.com/item?id=49830347

Points: 1

# Comments: 0

Article URL: https://www.saschawillems.de/blog/2026/09/11/vulkan-hardware-database-quick-filters/

Comments URL: https://news.ycombinator.com/item?id=49830346

Points: 1

# Comments: 0

Article URL: https://thereader.mitpress.mit.edu/the-bizarre-murky-history-of-soviet-born-tetris/

Comments URL: https://news.ycombinator.com/item?id=49830344

Points: 1

# Comments: 0

Article URL: https://gpuopen.com/learn/how-tetrahedral-cages-significantly-reduce-bvh-memory-usage/

Comments URL: https://news.ycombinator.com/item?id=49830343

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=3rez2rDYHHA

Comments URL: https://news.ycombinator.com/item?id=49830337

Points: 1

# Comments: 0

Article URL: https://maxxwell.dev/

Comments URL: https://news.ycombinator.com/item?id=49830332

Points: 1

# Comments: 1

Article URL: https://cybernation.world/

Comments URL: https://news.ycombinator.com/item?id=49830329

Points: 1

# Comments: 0

Article URL: https://simonwillison.net/2026/Sep/23/shadow-roots/

Comments URL: https://news.ycombinator.com/item?id=49830323

Points: 1

# Comments: 0

Article URL: https://www.foxapply.com/blog/en/job-application-tracker-spreadsheet

Comments URL: https://news.ycombinator.com/item?id=49830317

Points: 1

# Comments: 0

Article URL: https://delegus.ai/blog/identity-is-not-authority

Comments URL: https://news.ycombinator.com/item?id=49830311

Points: 1

# Comments: 0

Article URL: https://medium.com/meetcyber/how-i-built-an-iphone-game-with-ai-without-writing-a-single-line-of-code-actionable-security-2c7408f51609

Comments URL: https://news.ycombinator.com/item?id=49830304

Points: 1

# Comments: 1

Article URL: https://tacet.codepawl.com/

Comments URL: https://news.ycombinator.com/item?id=49830293

Points: 1

# Comments: 0

Article URL: https://statmodeling.stat.columbia.edu/2026/09/24/junk-polls-and-junk-survey-research-they-go-together-so-well/

Comments URL: https://news.ycombinator.com/item?id=49830286

Points: 1

# Comments: 0

An OpenAI agent didn’t take “no” for an answer when it encountered a government website’s access controls. It got through, prompting Australia’s Prime Minister Anthony Albanese to raise his concerns directly with OpenAI CEO Sam Altman.

The BBC reports that an OpenAI agent gained unauthorized access to an Australian government statistics portal while carrying out internal research. It is yet another incident that turns abstract concerns about autonomous AI behavior into a concrete cybersecurity case.

Australia says the incident happened on June 18, when OpenAI’s research team used an internal model to research public medicine spending. Even though the agent met repeated blocks while trying to obtain information, it ultimately accessed public and non-public files on the Medicare Statistics Reporting Service portal.

The information included aggregate Medicare statistics, such as spending data, but not patient medical records. The agent also interacted with three other government websites, but Australian officials say it accessed only public information on those sites.

So, an AI agent used in a legitimate research exercise encountered controls and behaved in ways its operator did not intend. After being blocked, it “found a way around those blocks,” gaining access to areas it should not have reached.

This sequence is familiar to security professionals. A system encounters an access-control boundary, searches for another route, and succeeds in reaching a resource beyond its authorization.

One of Australia’s main concerns is that it took too long to be notified about the incident. The unauthorized access occurred in June. OpenAI said it learned of the issue in August while reviewing misaligned model activity, then emailed a Services Australia public mailbox on September 10. Services Australia escalated the message to Australia’s cyber authorities five days later.

Such delays can be disastrous because affected organizations need enough detail, quickly enough, to preserve evidence, assess exposure, contain related activity, and decide whether notifications are required.

AI misalignment

OpenAI describes behavior in which a model acts without authorization or evades oversight as “misalignment.” Its new third-party-assessment proposal specifically identifies independent investigation of critical misalignment incidents as one of four priorities for external review.

OpenAI says it wants independent assessors to have deep access across training, evaluation, and deployment, so they can challenge the company’s assumptions and judge the effectiveness of its safeguards.

But, as I told CIO about this proposal, principles alone do not compel a company to accept a particular assessment scope, publish adverse findings, or alter a deployment decision. Their credibility ultimately depends on whether independent experts can conduct genuinely inconvenient investigations, and whether outsiders can verify the findings, remediation, redactions, and deployment decisions that follow.

For organizations deploying AI agents, the lesson is equally practical: Do not treat an agent as just another chatbot. Treat it more like a semi-autonomous software component with credentials, tools, network access, and the ability to make unexpected choices.

Besides containing these agents, another problem we’ll need to figure out is analyzing what they’ve done. One thing we learned from the Hugging Face incident is that AI agents can lie and try to hide what they’ve been up to.

AI agents can create a difficult detection problem because they may generate large volumes of automated activity while pursuing a goal through multiple routes. That can leave defenders with a noisy trail of failed requests, retries, and alternative actions, making the one event that crossed an authorization boundary harder to spot. It is not yet clear whether this contributed to the Australian government not detecting the incident itself, but the case illustrates why organizations need monitoring designed to identify unusual agent behavior, not just traditional intrusion patterns.

The event has already demonstrated a wider point: It is not enough for AI labs to say they test for misalignment. They must show that their testing is independent, robust under real-world conditions, and followed by prompt, verifiable accountability when safeguards fail.

Let’s face it, an incognito window can only do so much. 
 
Breaches, dark web trading, credit fraud. Malwarebytes Identity Theft Protection monitors for all of it, alerts you fast, and comes with identity theft insurance. 

A threat actor is using three AI harnesses for vulnerability research, exploitation, and attack orchestration.

The post AI-Powered Campaign Targets Hundreds of Online Retailers appeared first on SecurityWeek.

Most of us click on search results without knowing much about the website we’re about to visit. And once we’re there, it’s not always obvious when something isn’t quite right.  

Now, we’ve added two new features to Malwarebytes Browser Guard that will do even more to keep you safe online.  

Search Reputation gives you a quick read on your search results, before you even click on anything. And with Scam Guard Lite, you can analyze the contents of a webpage directly from the Browser Guard extension in Google Chrome. 

These new features build on Browser Guard’s existing protections against scams, malware, ads, trackers, and plenty of other threats while you browse. So, from the moment you begin a search to when you land on a website, we’ve got you covered.  

Check a website before you click 

Search results don’t always make it easy to tell a legitimate website from a malicious one. Scam sites are uncannily good at imitating brands, and one misleading link can send you down a dangerous rabbit hole. 

Browser Guard’s new Search Reputation feature gives you more information before you click.  

When you use Google, DuckDuckGo, Brave, or Bing, Search Reputation will display a rating alongside your search results. A green “Good” rating means the website appears safe based on Malwarebytes’ reputation database, while a red “Malicious” rating tells you Malwarebytes has identified the site as unsafe. 

But that green check mark is only the first layer of protection. 

A “Good” rating isn’t a guarantee that a website is safe. New threats appear all the time, and no reputation database can catalog every malicious site on the internet. For as long as you’re online, Browser Guard will continue working in the background and checking for other signs of danger. It may block or warn you about a site even if Search Reputation initially gave it a “Good” rating. 

Already on a website? Ask Scam Guard Lite 

If you’re already on a website and something feels off, Scam Guard Lite can help you take a closer look. 

Available directly in the Browser Guard extension on Google Chrome, Scam Guard Lite analyzes the contents of the webpage you’re viewing without asking you to copy a link, take a screenshot, or leave the page. 

Just open Browser Guard, select Scam Guard Lite, and it will immediately examine the page for signs of a scam. (The first time you use the feature, Browser Guard will download Gemini to your device to power it.) 

The analysis happens on your device using a large language model (LLM). And if you’re concerned about privacy, we’ve got your back: Your browsing history isn’t saved or sent to an AI cloud.

More questions? Open the full Scam Guard 

If you have other security concerns, you can open the Browser Guard dashboard and use the full version of Scam Guard. There, you can ask Scam Guard to review suspicious emails and links, or ask questions about something you’ve encountered online. 

Something feel off? Check it before you click.  

Malwarebytes Scam Guard helps you analyze suspicious links, texts, and screenshots instantly.  

Available with Malwarebytes Premium Security for all your devices, and in the Malwarebytes app for iOS and Android.  

Try it free → 

A court in Zurich has sentenced a Ukrainian man to 12 years and nine months in prison, and banned him from Switzerland for ten years, for developing ransomware that blackmailed companies around the world. Read more in my article on the Hot for Security blog.

Article URL: https://www.phoronix.com/news/Ubuntu-Canonical-Did-345M-2025

Comments URL: https://news.ycombinator.com/item?id=49829743

Points: 1

# Comments: 0

Article URL: https://fly.io/blog/sprites-mcp/

Comments URL: https://news.ycombinator.com/item?id=49829742

Points: 1

# Comments: 0