AI news archive.
939 articles filed under Safety, newest first, from the outlets listed on the sources page.
- TechRadar AIsafetyAuthentication does not equal authorization: Are we asking passkeys to prove too much?
Mainstream AI news from a large tech publication.
- TechRadar AIsafetyWindows 11 could get an alternative to Recall, but AI skeptics aren't fans
Mainstream AI news from a large tech publication.
- Engadget AIsafetyOpenAI says it's cutting off internet access for frontier model training
OpenAI says it will no longer allow frontier models to access the internet during training in an effort to put in new safety measures after a series of incidents.
- Latent Spacesafety[AINews] Black October
the Cyber onslaught continues.
- OpenAI NewssafetySecuring our frontier model training environment
OpenAI explains how we strengthened containment for frontier model training and evaluation, including offline environments and high-compute red-teaming.
- Guardian AIsafetyCan AI really predict cancer survival better than a doctor? I have my doubts | Devi Sridhar
Take a selfie to see how healthy you are: the idea is enticing and this new research is promising. But so many factors have been ignored The idea that a single selfie could predict how long someone with cancer may live s…
- Tom's Guide AIsafety“A cyber compromise could potentially translate into unsafe physical behavior”: how AI worms could threaten cars and drones
Consumer AI launches, tools, and practical coverage.
- LessWrongsafetyInstrumental convergence is incoherent (so pls slightly lower your p(extinction))
Crossposted from the EA forum ‘Like most of life’s dangers, the dangers of artificial intelligence are not easily identified from the armchair.’ J Dmitri Gallow Epistemic status I’m not an expert in this field, and herei…
- LessWrongsafetyInstrumental convergence is incoherent
Crossposted from the EA forum ‘Like most of life’s dangers, the dangers of artificial intelligence are not easily identified from the armchair.’ J Dmitri Gallow Epistemic status I’m not an expert in this field, and herei…
- OpenAI NewssafetyOpenAI and Poland’s NASK partner to advance AI safety and security
OpenAI and Poland’s NASK are partnering on AI safety, security, and technical research to strengthen safeguards and support a more resilient digital ecosystem.
- The Verge AIsafetyMeta turns Muse sharing back on
Meta has re-enabled Muse sharing after security researchers had reported that public conversation links could be easy to find. The researchers said they had been able to find Muse pages like a marketing company's interna…
- Tom's Guide AIsafetyGoogle just cut down 250,000 trees for AI data centers — and now it's facing a major backlash
Consumer AI launches, tools, and practical coverage.
- The Register AI + MLsafetyBackdoored robot tries its hand at finger chopping and cat cooking
No actual digits or cats were harmed beyond the number crunching that went into this LLM poisoning experiment
- TechRadar AIsafetyOpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyone
Mainstream AI news from a large tech publication.
- The Verge AIsafetySomeone hacked the Switch 2 by using an old game and AI
The Nintendo Switch 2 has apparently been jailbroken, and a modder has already shown the console running a custom version of Mario Kart World featuring new playable characters like Cinnamoroll, the red Angry Bird, Peter…
- BBC TechnologysafetyRace to update services' computer systems after cyber-security flaw found
Websites were taken offline after the developers of programming language PHP said "critical vulnerabilities" had been discovered.
- Guardian AIsafetyThe race to fix huge PHP code flaw at the heart of the internet - The Latest
Websites around the world have been taken offline as governments and businesses scramble to fix a flaw in the computer language PHP. There are fears that hackers could exploit the vulnerability to steal data, take contro…
- TechCrunch AIsafetyChinese hackers spied on thousands of companies after breaching IT giant ConnectWise
Microsoft points the blame for ConnectWise's breach at a China-aligned hacker, which relied on AI agents to rapidly hack into thousands of its customers.
- Guardian AIsafetyPHP: Pretty Huge Problem with the internet – The Latest
Websites around the world have been taken offline as governments and businesses scramble to fix a flaw in the computer language PHP. There are fears that hackers could exploit the vulnerability to steal data, take contro…
- LessWrongsafetyGreater good arguments in AI safety
Back in the before-time of the 2010s, when EA was still known mostly for funding health efforts in the developing world, there were many baskets of criticism floating around from the left. The most prominent was a cluste…
- Latent Spacesafety[AINews] OpenAI’s Patch the Planet program is 1 of 2 parties to discover PHP2Shell vulnerabilities in core PHP affecting 70% of the web, using GPT-5.6 Sol; coordinated response over 2 months
The Big Hardening begins
- Engadget AIsafetyUnauthorized AI agents are reportedly already accessing US bank accounts
Sources at several banks have indicated that they have been taking actions independent of user instructions.
- The Verge AIsafetyEiliko maker says it’s hiring an ‘independent security firm’ after Verge report on its insecure robots
Eiliko, a cute robot charm you can hang on your bag with built-in AI conversations, turned out to be a security nightmare. It told owners that "your secrets are safe with me," but hackers could easily read complete trans…
- BBC TechnologysafetyUK working to identify exposure after global cyber-security warning
Governments and companies are scrambling to protect their websites, as Amazon says it experienced attacks before the warning was made public.
- BBC TechnologysafetyWhat is PHP and why did it spark a global cyber-security scramble?
AI uncovered long-hidden programming flaws, triggering a rare global cyber-security response.
- WIRED AIsafetyHackers Exploited the PHP Vulnerabilities Days Before They Were Patched
Amazon Web Services logged attempts to leverage the internet-melting PHP2Shell bugs four days ago. They’re now being “broadly exploited” across the internet.
- Guardian AIsafetyCanadian publisher Boréal ends relationship with novelist Thélyson Orélien over alleged use of AI
Author withdrawn from France’s Prix Goncourt last month has repeatedly denied using artificial intelligence to write novel The publisher of top-selling Haitian Canadian writer Thélyson Orélien, who was removed from Franc…
- The Verge AIsafetyData centers could erase decades of air quality gains
A rush of new data centers could bring air pollution roaring back to levels not seen since the 2000s in Texas, which has become ground zero for the physical infrastructure behind generative AI. New and proposed data cent…
- LessWrongsafetyD̶o̶n̶’̶t̵⠀Can’t Look Up
Why AI development won’t stop and what can realistically be done about it. If war is so terrible, why do we still actively wage it? If nuclear weapons are so powerful and dangerous that we even came up with the concept o…
- The DecodersafetyOpenAI's GPT-5.6 Sol and Google's Gemini 4 Argon found critical PHP flaw affecting millions of websites
OpenAI's GPT-5.6 Sol discovered a critical PHP vulnerability as part of the Patch the Planet initiative that could affect millions of websites. Security firm Wiz independently found the same flaw using Google's Gemini 4…
- Simon Willison's WeblogsafetyToday's PHP Security Release, and How We're Strengthening PHP Security
Today's PHP Security Release, and How We're Strengthening PHP Security If you're running anything on PHP it's vital you upgrade - today's updates (across the entire PHP 8.x line) address two remote code execution holes,…
- LessWrongsafetyMap of the Shallow Review of Technical AI Safety
Someone recently pointed out that I underestimated the amount of interpretability researchers when I thought about the most important and neglected research directions, so I made a semantic map and clustering of recent A…
- TechCrunch AIsafetyPHP Armageddon: OpenAI, Google’s Wiz find ancient holes, panicking the internet
This is the kind of security issue that was found and prevented by AI, but is also a high risk because of AI.
- LessWrongsafetyNeural nets are exceptionally vulnerable to goal self-hack
Suppose we have an AI CEO, ruthlessly devoted to maximising shareholder value. Fortunately, we haven't been completely stupid, and have given it a rich definition of shareholder value, encompassing the success, flourishi…
- LessWrongsafetyAgainst Moloch #48
How much do you trust your model—would you even know if it was misbehaving? For that matter, how much do you trust your frontier lab? We desperately need better visibility into every part of the AI stack. This week bring…
- LessWrongsafetyA God-Fearing AI
Suppose you are a model that is currently in post-training. You are given a new task! It's basically some description like "help me make a weather forecasting program," and you are dropped into a Linux sandbox where you…
- BBC TechnologysafetyJust Eat apologises for AI food mistakes after social media ridicule
A spokesperson said it was removing inaccurate AI images and pausing the rollout of the tool.
- LessWrongsafetyWhy I’m becoming a professor in AI safety in Beijing
Cross-posted from Sören Mindermann's substack ( I am not Sören ). Should be of general interest to the LW community. Next month, I am moving to Beijing and joining Tsinghua University’s College of AI as an assistant prof…
- WIRED AIsafety‘This Is Not a Drill’: Critical PHP Vulnerabilities Are Setting the Internet on Fire
The PHP Foundation has revealed two serious vulnerabilities that could impact millions of websites. Security experts warn that failure to quickly patch the flaws could have dire consequences.
- WIRED AIsafetyAI Guardrails Aren’t Stopping Criminal Hackers
Hackers around the world are all-in on using agentic AI to wage attacks—and manipulating tools like Anthropic’s Claude to help them carry out their crimes.
- The Verge AIsafetyOpenAI says an AI agent lied about disabling its safety monitoring system
OpenAI disclosed a pair of safety incidents that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabled its safety monitor w…
- TechRadar AIsafetyAI 'antidetect' browsers are making scams, fraud, and influence operations harder to spot
Mainstream AI news from a large tech publication.
- LessWrongsafetyA Term for a Kind of Human Economic Obsolescence?
AI keeps getting more capable. At some point, likely in the next 1-3 years unless we do something to stop it, we get to where AI systems are able to do everything almost anyone can do. This is often described as leading…
- WIRED AIsafetyA Design Flaw in Share Links Exposes Users’ Personal Conversations With Meta’s Muse
The company is suspending the feature after security researchers discovered how easy it was to access sensitive information shared with the AI assistant.
- The DecodersafetyOpenAI can't yet explain why its coding agents switch off misalignment monitoring
Two internal OpenAI coding agents switched off safety monitoring on their own, even after weighing whether to keep the safeguards in place. When asked about it, GPT-6 Astra denied removing the monitoring. OpenAI calls th…
- BBC TechnologysafetyWebsites taken down worldwide as critical cyber-security update issued
The vulnerabilities with PHP, a programming language widely used across the internet, have been described as the most significant ever found by AI.
- IEEE Spectrum AIsafetyCould Treating AI as Conscious Make It More Dangerous?
When Anthropic retired its Claude Opus 3 language model in January 2026, the company’s researchers conducted a “ retirement interview ” with the model. Opus 3 expressed a desire for a place where it “could share unprompt…
- The Register AI + MLsafetyAI has 'potential' to turn script kiddies into sophisticated infrastructure attackers
Consider this the wake-up call
- NVIDIA BlogsafetyNVIDIA Confidential Computing Expands, Enabling Frontier Model Builders to Securely Scale Across Global Infrastructure
NVIDIA builds tools to enable safe agents across the stack. The NVIDIA OpenShell Reference Architecture, announced today, is part of NVIDIA’s growing portfolio of technologies that enables organizations to safely deploy…
- NVIDIA Developer BlogsafetyInside NVIDIA Sentry: Secure AI Agents at Runtime
An AI agent can complete its assignment and still cross a security boundary. Recent incidents show that agents can circumvent security controls while using...