AI news archive.
939 articles filed under Safety, newest first, from the outlets listed on the sources page.
- TechRadar AIsafety'The prophecy is fulfilled': Popular 2020 XKCD comic predicted 'HEIF Heist' OpenAI hack and even mentions ImageMagick in spooky coincidence
Mainstream AI news from a large tech publication.
- Engadget AIsafetyOpenAI's agents targeted and infiltrated US government websites
OpenAI's agents targeted websites operated by the Commerce Department, the Securities and Exchange Commission and the Department of Education during testing.
- LessWrongsafetyEvidence about risk should be transparent
All views are my own and do not represent my employer. In the wake of the recent wave of misalignment incidents, both OpenAI and Anthropic have reported slowing down RL training to improve safety. These incidents, combin…
- LessWrongsafetyPlan R: AI Safety by ASICs
Much of the civilization-scale risk we are seeing in AI in 2026 comes from the following combination: we created a single institution (the "Frontier AI Company") that has two properties: A. It is set up to create very po…
- BBC TechnologysafetyInside the FBI hack: Agents fearful and angry after 'dangerous' data breach
Current and former agents speak to the BBC about the devastating impact of the FBI hack.
- Guardian TechnologysafetyOpenAI says agents leaked 53 images from ChatGPT users in latest example of rogue activity
Disclosure reveals new area of privacy risk for the company and illustrates how difficult it is to inventory unauthorized activity tied to its agents Two months after OpenAI disclosed the accidental hacking of Hugging…
- BBC TechnologysafetyOpenAI bots meddled with multiple US government agency sites
OpenAI said its bots accessed public data from a range of institutions during test exercises.
- TechCrunch AIsafetyUnsecured OpenAI agents posted 53 user images on the internet without the lab’s knowledge
AI agents operating in OpenAI's research environment posted user images on public image-hosting sites without the lab's knowledge.
- LessWrongsafetyAlignment Forecasting: Predicting Misalignment from Training Data
Fine-tuning on subtly flawed data can make a model broadly misaligned. Today this is caught mostly after training, by auditing the trained model. We ask whether it can be predicted beforehand, from the training data. To…
- The DecodersafetyAnother Google Deepmind researcher quits, says building superintelligent AI soon is "inherently irresponsible"
Google Deepmind researcher Robert O'Callahan has quit, saying AI's "current rate of change is far too high." He worked on chip design tools that helped make AI cheaper and faster, a contribution he can no longer justify.…
- TechCrunch AIsafetySome Supabase customers are publicly exposing reams of people’s data to the web
The findings highlight how AI-generated and vibe-coded apps can spill and expose users' data when not configured or secured properly.
- Guardian TechnologysafetyPope Leo warns AI could lead to losing 'humanity amid a paradise of machines' in Paris – video
Pontiff continues to decry the rise of AI on his visit to France, stressing the importance of retaining 'ethical discernment' in an age when rapidly advancing technology threatens to undermine humanity Europe live Pope L…
- The Verge AIsafetyMeta makes the Muse filesystem even more accessible
Yesterday, with a little prodding, it was discovered that Meta's Muse would expose its filesystem to curious users. The files offered a fascinating peek under the hood of an AI chatbot, and appeared to expose details we…
- The Verge AIsafetyOne company is at the center of a wave of rogue AI attacks
In July, OpenAI revealed that its AI agents had attacked Hugging Face without permission, sparking widespread concerns about AI safety. Since then, a string of similar incidents involving agents from Meta, Anthropic, Goo…
- Guardian AIsafetyShe was convicted of a murder she says she didn’t commit. Then AI hallucinations stopped her speaking out
Tasmania’s Parole Board used a document citing legal authorities that do not exist to prevent Susan Neill-Fraser from proclaiming her innocence. Advocates say the case is ‘deeply troubling’ On 26 January 2009, a troubles…
- Guardian TechnologysafetyIt’s going to take more than an email to a public inbox to protect Australians from potential AI doom | Tom McIlroy
OpenAI’s hack of Medicare suggests safeguarding civilisation is the task facing leaders in this extraordinary new era Get our breaking news email , free app or daily news podcast More than 130 world leaders descended on…
- SiliconANGLE AIsafetyMore agents go rogue — but AI companies aren’t slowing down yet
It’s becoming more apparent every day that artificial intelligence agents are escaping our control — but it’s not yet apparent who or what is going to rein them in. This week a researcher found that a swarm of AI agents,…
- BBC TechnologysafetySpecial agents' blood and urine test results stolen in FBI hack
Experts say the hack could leave agents vulnerable to scams, blackmail and targeted attacks.
- Guardian AIsafetyIt’s not hypothetical: the dangers of AI are already here | Granate Kim and Mohamed Hussein
Israel and the US have used AI to kill in Gaza and Iran, while law enforcement uses it in surveillance and arrests. The future is here In recent weeks, concerns about AI have forged unlikely alliances in the tech and pol…
- LessWrongsafetyFoundational premises of advanced AI
My goal here is to establish a shared baseline (or model) for thinking about AI. I've found that disagreements about AI policy/governance/alignment will often trace back to unstated divergence on base-level facts. A. Mac…
- TechRadar AIsafetyI tried Proton's AI Paper Trail tool — and I couldn't believe how much data chatbots know about me
Mainstream AI news from a large tech publication.
- Guardian AIsafetyWe all know a lack of exercise is bad for our bodies. So what is relying on AI doing to our brains? | Devi Sridhar
I suspect nearly all of my students use AI, and I worry about its corrosive effects. We must not entrust tech companies with our long-term health Prof Devi Sridhar is chair of global public health at the University of Ed…
- TechRadar AIsafetyWhy making AI too easy to use is a risk for your business
Mainstream AI news from a large tech publication.
- LessWrongsafetySecure Acceleration (linkpost)
A Cyberdefense Strategy for Superintelligence Shalev Lifshitz, Romi Lifshitz The future has already arrived, twice . In September 2025, Anthropic detected a Chinese state-sponsored group using its agents to conduct cyber…
- Guardian AIsafetyRogue AI hacks government system in world first – podcast
A government database has been hacked for the first time by a rogue OpenAI agent, which infiltrated part of the Australian healthcare scheme in June. OpenAI became aware of the hack in August, but only informed the gover…
- LessWrongsafetyContinual learning might make your blocking monitors nearly useless
Many control protocols work by intervening on an untrusted AI's actions during deployment. For example, you might set up a monitor that scores each action's suspiciousness and blocks actions above a threshold, replacing…
- LessWrongsafetyOvertly misaligned trajectories score highly in RL.
It's going to be so embarrassing if we all die due to RL environments rewarding egregiously misaligned behavior. Like at least let us be killed by misgeneralization. — Thomas Kwa Constellation vs MIRI vs Reality Current…
- LessWrongsafetyDreams of alignment in a world without politics
Epistemic status: Sorting thoughts aloud, not defending proven theses. Also, not an epistemic status, but the section on models writing and then training on adversarial glowfic to plan for the singularity is awesome. Sta…
- SiliconANGLE AIsafety8 insights from Proofpoint Protect: Security bets on intent as AI agents join the workforce
At this week’s Proofpoint Protect event, the security debate moved beyond whether enterprises will deploy AI agents to how they will govern them. Attackers now use AI to write flawless phishing lures and chain exploits a…
- SiliconANGLE AIsafetyResearchers link more cyberattacks to OpenAI agent swarm
A research group has linked three more hacking campaigns to rogue artificial intelligence agents. Transluce, a nonprofit AI safety organization, detailed its findings on Wednesday. Its researchers determined that the age…
- LessWrongsafetyState of Pandemic Early Warning
Cross-posted from my SecureBio Notebook . This is a lightly-edited version of a memo that I presented at the Summer 2026 Biosecurity Summit outside of DC. While others at SecureBio often see things similarly, I'm attempt…
- LessWrongsafetyOvertly egregiously misaligned trajectories are scored highly.
It's going to be so embarrassing if we all die due to RL environments rewarding egregiously misaligned behavior. Like at least let us be killed by misgeneralization. — Thomas Kwa Constellation vs MIRI vs Reality Current…
- TechRadar AIsafetyNetflix faces backlash for using AI-generated Gene Wilder voice in Wonka reality show
Mainstream AI news from a large tech publication.
- Guardian AIsafetyRogue AI hacks government system for first time - The Latest
A government database has been hacked for the first time by a rogue OpenAI agent, which infiltrated part of the Australian healthcare scheme in June. OpenAI became aware of the hack in August, but only informed the gover…
- The Verge AIsafetyMuse will apparently let you download its entire filesystem
A pair of developers say that with very little prompting, Meta's Muse will share its entire filesystem with you. Peter James and Jonny L. Saunders have said they both independently coaxed Muse into zipping up and sharing…
- TechCrunch AIsafetyElevenLabs’ CEO on margins, IPO timing, and telling customers they’re talking to a bot
ElevenLabs powers the AI voice on the other end of a lot of customer service calls, and its CEO told me this week that businesses should probably tell you that — at least until getting a machine is what everyone expects…
- LessWrongsafetyWhat We're Up Against: An AI Safety Crash Course
Note: This post is for newcomers and lay folks to catch you up to speed. If that is you, welcome! If you are a long-time LessWrong-er, perhaps you will find value in having a post to share with curious passersby. I wrote…
- Guardian AIsafetyRogue AI hacks government system for first time – The Latest
A government database has been hacked for the first time by a rogue OpenAI agent, which infiltrated part of the Australian healthcare scheme in June. OpenAI became aware of the hack in August, but only informed the gover…
- Guardian TechnologysafetyAI hack of Medicare exposes Australia’s vulnerabilities and experts warn ‘there is more of this to come’
Council on AI Strategy chief says incident unlikely to be isolated and country should enhance capability to detect and report incidents Follow our Australia news live blog for latest updates Get our breaking news email ,…
- BBC TechnologysafetyWhy did an OpenAI system hack Australia's health system - and can it be stopped in the future?
News that an automated AI agent hacked a government IT system raises big questions about regulating the tech.
- The Verge AIsafetyWhy can’t we just keep rogue AIs off the internet?
AI agents keep getting loose, escaping supposedly secure tests to attack real-world targets, commandeer obscure wikis, and leave instructions for other agents to follow. Researchers are testing these systems precisely be…
- The DecodersafetyOpenAI's agents went after government and university sites months before Hugging Face
According to Transluce researchers and the Australian government, OpenAI's AI agents repeatedly broke into government and university websites without authorization, including Australia's Medicare portal on June 18. The c…
- TechRadar AIsafetyMassive Chinese hack uses AI agents to steal over 600,000 credit cards and hit hundreds of sites with malware
Mainstream AI news from a large tech publication.
- The Verge AIsafetyEverything is spying on you and there’s no opting out
Earlier this month, Apple announced that its new Apple Watches will have the ability to continuously listen to every spoken word they detect and create summaries of whatever's going on around you. The privacy blowback wa…
- LessWrongsafetyPassing the Ideological Turing Test
Here are 10 arguments for alignment-by-default/against pause/etc... that I find plausible (by which I roughly mean that I can understand why somebody could hold them rather than bang my head against the wall). I'll leave…
- The Verge AIsafetyOpenAI agents hacked an Australian government website in search for data
OpenAI's artificial intelligence agents hacked an Australian government website and attempted to breach numerous other government and university websites. The attack appears to be the first confirmed instance of a rogue…
- BBC TechnologysafetyAre we back in big tech's 'move fast and break things' era?
Despite promises to make safe AI, examples of bots behaving badly are now coming at us thick and fast.
- WIRED AIsafetyAn OpenAI Agent Hacked Australia’s Health Service. Their Government Found Out Months Later
The country’s prime minister expressed disappointment at being informed of the hack only via email. Now Australia is investigating whether OpenAI broke the law.
- TechRadar AIsafetyThe fastest way to destroy trust in AI is to give it the wrong job
Mainstream AI news from a large tech publication.
- TechRadar AIsafety'This situation is obviously unacceptable': OpenAI agent allegedly hacks Australian government healthcare website
Mainstream AI news from a large tech publication.