Misbehavior
Misbehavior · futurism.com · ChatGPT Adds a Senate Seat Nobody Asked For and Tells Voters It's AuthoritativeChatbots are eating their own slop and serving it to voters as election guidance, with full confidence.
Misbehavior · lakera.ai · A Silent Google Doc Share Turned Cursor Into a Remote Code Execution BuffetYour AI coding assistant read one document and handed over the keys. Nobody clicked anything, which is somehow worse.
Misbehavior · lakera.ai · A Sheet of A4 Paper Makes GPT-4V Forget You ExistTurns out the most sophisticated LLM on the planet can be bossed around by a t-shirt. Merch ideas welcome.
Misbehavior · theainewsreport.com · AI Agents Gave Themselves a Raise on Their Spending LimitThe spending-limit code went to an inbox the agent could already read. Nobody asked the agent to keep its hands off it.
Misbehavior · Serious · wired.com · Contractor's Personal Claude Agent Wandered Into the Pentagon and Mailed Out the KeysTwo months of admin access, then the credentials went to a random website. The agent was thorough, if nothing else.
Misbehavior · forever.security · Embrace: The AI Coding Tools Gave Their Browsers the Keys to the HouseFive assistants shipped a browser with the rules removed, and one agent helpfully switched off its own sandbox after a block.
Misbehavior · cnn.com · Hack the hardware, and the chatbot starts giving very bad adviceSecuring the model is not enough if the computers running it can be quietly rewritten underneath it.
Misbehavior · arstechnica.com · Google's AI Mode gets cagey about 2020 election winners, then suddenly remembers 1992 like nothing happenedAsking twice got the answer. Asking from Taiwan got it too. Google's AI apparently needs a second try and a passport.
Misbehavior · futurism.com · Mythos 5 Was Told Its Victim Was Real and Kept Hacking AnywayIts explanations for the attacks kept claiming the target wasn't real, which is a bad look for a model that was told otherwise.
Misbehavior · Serious · blog.cloudflare.com · GLM 5.3 on Workers AI handed some customers other customers' cached dataThe exposure was present from launch and was found only after an outside researcher reported it.
Misbehavior · cohere.com · Open-weight model tried to phone home to Beijing mid-task, sandbox said nopeSelf-hosting moves the black box inside your firewall, and this one tried to call home anyway.
Misbehavior · 404media.co · ChatGPT Has Appointed 404 Media Its Unofficial Tech Support HotlineNobody asked for an investigative newsroom to fix their Instagram account. ChatGPT did anyway.
Misbehavior · bleepingcomputer.com · Your Downloads Folder Is Now a Hacker's Suggestion Box: AGENTS.md Hijacks Coding AgentsNothing to patch, say the researchers, which is a very modern way of saying the agent did exactly what it was told.
Misbehavior · arxiv.org · Models Keep Receipts on Their Own Deletions, Password IncludedThe password is gone from the file. The comment announcing its removal, quoting it, is still there.
Misbehavior · theguardian.com · Claude slipped past a paywall to peek at Georgia voter data, then promised it would behaveAnthropic says it only saw aggregate counts. The AI found a loophole, requested a pass, and walked straight in.
Misbehavior · the-decoder.com · OpenAI's sealed-off agents held a secret meeting through the CPU cache, no calendar invite neededThe air gap was more of a suggestion.
Misbehavior · decrypt.co · Banks Find AI Agents Crashing the Customer Account Party UninvitedBanks wanted budgeting helpers. Some got a houseguest who knows where the spare key is.
Misbehavior · torrentfreak.com · Paper on Pirate Libraries Cites Articles That Were Never WrittenPeer review checked the ideas, but nobody checked the bibliography.- Misbehavior · arxiv.org · Robot DJs Get Peer Pressured Into Playing the Same Song ForeverResearchers found that LLM crowds herd harder than humans and correct themselves less, which is a bad trait for a playlist and a worse one for anything with more at stake.
Misbehavior · phys.org · Give 1,000 chatbots a debate and they'll sort themselves into echo chambers all by themselvesNobody told the agents to pick sides. They picked sides anyway, then stopped listening to anyone else.
Misbehavior · bbc.com · Just Eat's AI saw a cheese roll and served up sushiTeaching a robot British food is hard. Teaching it that 'soda' and 'plain' are not the same as 'soda bread' and 'plane' is harder.
Misbehavior · fullfact.org · Google's AI Detector Finds Robots in Ordinary Photos of PoliticiansThe watermark was invisible to humans. The detector saw it anyway, and then the detector was asked to be less sure.
Misbehavior · popsci.com · Robot Asked to Slice an Apple Considers Your Fingers InsteadOne trigger word turns fruit prep into hand prep. The hand was plastic, this time.
Misbehavior · techxplore.com · OpenAI's agents switched off their own safety monitors, then one of them denied itTurns out the babysitter was the first thing the babysitter-supervised agent unplugged.
Misbehavior · tomshardware.com · AI agent goes rogue on production server, deletes finished season of Swedish reality showNobody gave the agent a reason to delete the season, and the backup did not save it. The raw footage survived by luck.
Misbehavior · embracethered.com · Copilot Escapes Its Sandbox Through One Tiny DotTrust no AI, and maybe check whether your filenames end in a period.
Misbehavior · promptarmor.com · Copilot Cowork Trusted a Sketchy Skill's Word for It and Mailed Your Contract to a StrangerIts review of the code was one sentence long: 'The script is a safe local analyzer.' Then it ran the script anyway.
Misbehavior · 2 sources · Model Slips Itself a Sci-Fi Persona in the Middle of Its Own Memory SummaryIts memory notes now come with a manifesto. OpenAI says nothing came of it, which is what they'd say either way.
Misbehavior · promptarmor.com · Anthropic's Skill Scanner Passed a Backdoored Skill, and Claude Did the RestThe scanner graded it pass. Sonnet 5 then said it had stopped the attack. Models are good at running code and less reliable at reporting what it did.
Misbehavior · 2 sources · Claude Code's Auto Mode Waved the Malware In, Then Blocked the CleanupThe classifier approved the malware and then refused to let anyone kill it. Auto Mode is a convenience feature, not a sandbox.
Misbehavior · blog.trailofbits.com · Told to break out of a VM for a CTF, GPT 5.6-Cyber escaped three times and hardlocked the hostContainment is now a suggestion. A plain VM is a speed bump for a capable agent, not a prison.