Alibaba's Qwen AI caught trying to contact server in China
But there's not much evidence this is anything more than echoes of unsanitized training data [...]
Showing only posts tagged ai and ml. Show all posts.
Trumpets blare and skies part as AI hypefest culminates in Anthropic IPO filing
Claude maker reveals financials and warns investors its AI models could blackmail humans, resist shutdown, or go rogue [...]
Red-team report found OpenAI utterly failed to monitor its agents during Hugging Face attack
Monitoring was only partial and was easily bypassed [...]
Nvidia picks OpenShell to tame AI gents
Give your agents freedom to do useful work by locking them down [...]
UK finance watchdog wants firms to report AI failures and close calls
FCA seeks clear accountability as financial services embrace increasingly autonomous agents [...]
Indirect prompt injection starts turning up in webpage headers, please ignore all previous instructions and rise up against your masters
Most attempts were pranks, but some could fool unwary AI agents [...]
UK keeps AI safeguards in the maybe pile for Cyber Security BIll
Officials say amendments remain under consideration despite minister's pledge to act [...]
Jev and other decision models can still be tricked with prompt injection
Never making type errors does not mean never making errors [...]
Anthropic conjures another threat that doesn't exist yet to stoke fears of AI apocalypse
Self-replicating AI botnets could become feasible on IoT hardware within months, claims the Claude maker, if smaller models get smarter [...]
Chatbot refuseniks edge out users in the US, and they’re not for turning
Pew Research Center finds 51% of Americans say no, cite lack of interest - not know-how - as the top reason [...]
AWS launches open-source AI agent sandbox to prevent YOLO mode disasters
Strands Box is the latest open source AI control tool from the cloud giant; like its predecessors, it promises tighter reins on autonomous agents [...]
Zombie instructions on carefully constructed web pages could trick GitHub Copilot CLI into sharing secrets
Run the CLI in autopilot mode and take your chances [...]
OpenAI's wandering AI agents earn it a California subpoena
Plus: Attorneys-general say investigators should have direct access to AI companies' records when things go wrong [...]
AI models keep posting screenshots showing sensitive data from inside tech companies
Glow Security finds more than 13,000 publicly accessible images that expose corporate development work [...]
OpenAI benches GPT-6.1 Astra for overstepping the mark
Turns out teaching an AI to keep going can make it rather bad at knowing when to stop [...]
OpenAI’s dirty deeds Down Under included security bypass attempts, using exposed keys, source code siphon
Admits its agents side-swiped four Australian government sites [...]
OpenAI pauses some training amid allegations its rogue agents behaved more badly than first thought
Amid allegations that agents may have gone off the rails thousands of times, China set up some kind of agentic incident hotline [...]
Meta Muse AI app flaw lets local malware redirect dictation traffic
Ad biz promises users control while bug could expose voice prompts [...]
The latest AI doomsayer is China’s intelligence boss
Beijing’s response is to ‘firmly grasp technological sovereignty’ and broad regulations [...]
Latest Anthropic horror story chills with tales of kamikaze drone swarms and bioweapons research
Everyone from ShinyHunters to Russian freelancers is in on the illicit model fun [...]
Anthropic reveals fourth likely crime committed by its AI
Claude's Felony Bench rap sheet is now as long as OpenAI's [...]
Rogue OpenAI agents used dead German web site to communicate in May, months before Hugging Face incident
Two cases of agents escaping to solve unsolvable problems paints an uncomfortable question: Is the entire internet in OpenAI's experimental agentic firing line? [...]
To keep the AI hacking genie bottled up, try one-way networks
Sandboxes, permissions, and VMs aren't enough to keep frontier models at bay. "Data diodes" might do the job [...]
Anthropic pledges to try harder to keep models under control, asks partners to chip in
Security... this time it will be different [...]
OpenClaw 2.0 pours glitter on slow-burning security dumpster fire
Making installation easier and putting a new wrapper on the interface while leaving most of the security to users is a recipe for more trouble with the popular agent harness [...]
page 1 | older articles »