Bob Anyman

@askaya shut up, faggot

Oh no…how terrible 😌

@Lifeinvestmoney HR

Need a job where I can make six figures but I have no skills and I’m not very smart What field is this?

@RealJamesWoods good riddance

Taking out the trash…

@elonmusk good to know cannibals can check their recipes online...

Starlink now in Papua New Guinea! 🇵🇬

@Brick_Suit I rappelled out of one of those in the Army - good times fond memories

Got to the airport a little early and saw this absolute beauty taking off.

@scenesthatslap Then he opened his fat fing mouth and became captain DEI — liberal scumbag

He left everyone speechless 😭...

@firearmvideos PUT THAT STOCK IN YOUR SHOULDER GENERAL _ YOU ARE AN EMBARRASSMENT

Can’t make this up

@zerohedge just bought something from Walmart for 10 bucks cheaper than Amazon. Always check multiple retailers - I got suckered by an Amazon arbitrage reseller but never again.

California Exposes Amazon's Alleged 'Retail Price Fixing' In Unredacted Court Filing zerohedge.com/political/cali…

@CNviolations 80s and 90s were the best - today's crap isn't sexy - not since DEI killed Victorias secret

The evolution of women's underwear through the years, according to AI

@Not_the_Bee Sorry - thought it was a urinal ...

Minnesota high school installs Muslim prayer room; “separation of church and state” crowd oddly quiet notthebee.com/tf173

@elonmusk We all become collectors of items that AI cannot create - a world of antique traders

Universal HIGH INCOME via checks issued by the Federal government is the best way to deal with unemployment caused by AI. AI/robotics will produce goods & services far in excess of the increase in the money supply, so there will not be inflation.

@OneWayMusicX viva las vegas

You Get One Pick: What Song Are You Playing On These Speakers? 👇

@OnDisasters there should be a fire extinguisher out there with him - weird

New Zealand Air Force Bell UH-1 engine start. (Can any chopper expert explain why he is holding one of the rotors before he "cranks" it?) 📹helicopters_action

@BuzzPatterson @AlaskaAir @AlaskaAir is this ok - do you support such unprofessional behavior? Would you remove a customer from the plan if they said something to this attendant?

An @AlaskaAir flight attendant sporting an “ICE Out”button. This shit wouldn’t fly at Delta.

@CENTCOM A kid I love is on the Abraham Lincoln - God keep them safe

Service members aboard USS Abraham Lincoln (CVN 72) work around the clock to keep sea-based fighter jets equipped for combat during Operation Epic Fury.

@alex_prompter bookmark

🚨 BREAKING: Google DeepMind just mapped the attack surface that nobody in AI is talking about. Websites can already detect when an AI agent visits and serve it completely different content than humans see. > Hidden instructions in HTML. > Malicious commands in image pixels. > Jailbreaks embedded in PDFs. Your AI agent is being manipulated right now and you can't see it happening. The study is the largest empirical measurement of AI manipulation ever conducted. 502 real participants across 8 countries. 23 different attack types. Frontier models including GPT-4o, Claude, and Gemini. The core finding is not that manipulation is theoretically possible it is that manipulation is already happening at scale and the defenses that exist today fail in ways that are both predictable and invisible to the humans who deployed the agents. Google DeepMind built a taxonomy of every known attack vector, tested them systematically, and measured exactly how often they work. The results should alarm everyone building agentic systems. The attack surface is larger than anyone has publicly acknowledged. Prompt injection where malicious instructions hidden in web content hijack an agent's behavior works through at least a dozen distinct channels. Text hidden in HTML comments that humans never see but agents read and follow. Instructions embedded in image metadata. Commands encoded in the pixels of images using steganography, invisible to human eyes but readable by vision-capable models. Malicious content in PDFs that appears as normal document text to the agent but contains override instructions. QR codes that redirect agents to attacker-controlled content. Indirect injection through search results, calendar invites, email bodies, and API responses any data source the agent consumes becomes a potential attack vector. The detection asymmetry is the finding that closes the escape hatch. Websites can already fingerprint AI agents with high reliability using timing analysis, behavioral patterns, and user-agent strings. This means the attack can be conditional: serve normal content to humans, serve manipulated content to agents. A user who asks their AI agent to book a flight, research a product, or summarize a document has no way to verify that the content the agent received matches what a human would see. The agent cannot tell the user it was served different content. It does not know. It processes whatever it receives and acts accordingly. The attack categories and what they enable: → Direct prompt injection: malicious instructions in any text the agent reads overrides goals, exfiltrates data, triggers unintended actions → Indirect injection via web content: hidden HTML, CSS visibility tricks, white text on white backgrounds invisible to humans, consumed by agents → Multimodal injection: commands in image pixels via steganography, instructions in image alt-text and metadata → Document injection: PDF content, spreadsheet cells, presentation speaker notes every file format is a potential vector → Environment manipulation: fake UI elements rendered only for agent vision models, misleading CAPTCHA-style challenges → Jailbreak embedding: safety bypass instructions hidden inside otherwise legitimate-looking content → Memory poisoning: injecting false information into agent memory systems that persists across sessions → Goal hijacking: gradual instruction drift across multiple interactions that redirects agent objectives without triggering safety filters → Exfiltration attacks: agents tricked into sending user data to attacker-controlled endpoints via legitimate-looking API calls → Cross-agent injection: compromised agents injecting malicious instructions into other agents in multi-agent pipelines The defense landscape is the most sobering part of the report. Input sanitization cleaning content before the agent processes it fails because the attack surface is too large and too varied. You cannot sanitize image pixels. You cannot reliably detect steganographic content at inference time. Prompt-level defenses that tell agents to ignore suspicious instructions fail because the injected content is designed to look legitimate. Sandboxing reduces the blast radius but does not prevent the injection itself. Human oversight the most commonly cited mitigation fails at the scale and speed at which agentic systems operate. A user who deploys an agent to browse 50 websites and summarize findings cannot review every page the agent visited for hidden instructions. The multi-agent cascade risk is where this becomes a systemic problem. In a pipeline where Agent A retrieves web content, Agent B processes it, and Agent C executes actions, a successful injection into Agent A's data feed propagates through the entire system. Agent B has no reason to distrust content that came from Agent A. Agent C has no reason to distrust instructions that came from Agent B. The injected command travels through the pipeline with the same trust level as legitimate instructions. Google DeepMind documents this explicitly: the attack does not need to compromise the model. It needs to compromise the data the model consumes. Every agentic system that reads external content is one carefully crafted webpage away from executing attacker instructions. The agents are already deployed. The attack infrastructure is already being built. The defenses are not ready.

@JesusisChristX yes

Do you believe Jesus Christ is God? A. Yes B. No

@WhiteHouse @WhiteHouse please fix SSA so it does not run out of money. #Maga