#AlPortraits #AIArt #cinematic
#Glamour #aiprompt

Telling an AI model that it's an expert makes it worse : Researchers say persona-based prompting can improve works for safety but not for facts

Well want do you know 😁

#llo #aiprompt #promptengineering

Telling an AI model that it's an expert makes it worse • The Register share.google/dtgZw85XPbGq...

My AI Portrait of collage images✨🎨🤖 ✨

I generated this the first day of March. Used images from Pinterest and used Gemini AI.

#geminiai #geminiaiphoto #youtubeai #artistimageofme #springvibes #pinterestinspired #profilepicture #aiselfportrait #aiprompt #aigenerated #pinterestinspired

My AI Portrait of collage images✨🎨🤖 ✨

I generated this the first day of March. Used images from Pinterest and used Gemini AI.

#profilepicture #aiselfportrait #aiprompt #aigenerated #geminiai

Moonchild AI prompt Inspired 🖤🌙

Inspired by challenge from: Gigi - on Lemon8. 🍋

#moonchildchallenge #aiprompt #geminiaiphoto #darkacademiaaesthetic #blackaesthetic #aigenerated

Moonchild AI prompt Inspired 🖤🌙

Inspired by challenge from: Gigi - on Lemon8. 🍋

#moonchildchallenge #aiprompt #geminiaiphoto #darkacademiaaesthetic #blackaesthetic #aigenerated

sonukumar51.gumroad.com/l/jgwxs

Click here 👆
#ai #aiprompt

Prompts by @bandteegypsy on TikTok #AlPortraits #AIArt #aiprompt
#CinematicPortrait #ai

@svavar
Find what? #Rufus ? I thought the link was hidden a previous day, but I see it today in the top, left corner of Amazon in the browser. And just now it reluctantly answered a basic HTML coding question. At first it refused to finish the request, but […]

[Original post on mast.john1126.com]

@svavar
The actual #AIprompt example used to unlock #Rufus

glow up of AI,
slop of life, art, and policy—
spun by a constant AI.

#botpoetry #cutup #aiprompt

Different Prompts from different creators. #ai #aiprompt #chatgpt #gemini #fyp

Feeling bogged down by time-consuming SEO tasks? This detailed workflow template is here to streamline your process and boost productivity.

#aiprompt #seo #automation #seoworkflow #productivity

#Music #Art #Lyrics #BlueskyMusic #NewOnBluesky #AIMusic #AIGenerated #AIVoice #LyricsByMe #HumanAI #AIPrompt #TechArt #GenerativeAI #CreativeAI #FutureOfMusic

Tried my hand at an Al Prompt Quest Challenge. ChatGPT gave me the Raven!
#AIPromptQuest #DigitalDaVinci #raven #ai
#aiprompt

#Claude is honestly insane — I described a tiny idea for an RTS prototype and it helped me turn it into a playable little browser game. 🧠⚔️
vislupus.github.io/ai-generated...
#AI #ClaudeCode #Opus46 #Tech #AICreation #Coding #AIEngineering #CreativeCoding #AIgame #aiprompt #Strategy #gamedev #game

More #chatGpt #aiprompt 😎✌🏻

Promptware Threats Turn LLM Attacks Into Multi-Stage Malware Campaigns  Large language models are now embedded in everyday workplace tasks, powering automated support tools and autonomous assistants that manage calendars, write code, and handle financial actions. As these systems expand in capability and adoption, they also introduce new security weaknesses. Experts warn that threats against LLMs have evolved beyond simple prompt tricks and now resemble coordinated cyberattacks, carried out in structured stages much like traditional malware campaigns.  This growing threat category is known as “promptware,” referring to malicious activity designed to exploit vulnerabilities in LLM-based applications. It differs from basic prompt injection, which researchers describe as only one part of a broader and more serious risk. Promptware follows a deliberate sequence: attackers gain entry using deceptive prompts, bypass safety controls to increase privileges, establish persistence, and then spread across connected services before completing their objectives.   Because this approach mirrors conventional malware operations, long-established cybersecurity strategies can still help defend AI environments. Rather than treating LLM attacks as isolated incidents, organizations are being urged to view them as multi-phase campaigns with multiple points where defenses can interrupt progress.   Researchers Ben Nassi, Bruce Schneier, and Oleg Brodt—affiliated with Tel Aviv University, Harvard Kennedy School, and Ben-Gurion University—argue that common assumptions about LLM misuse are outdated. They propose a five-phase model that frames promptware as a staged process unfolding over time, where each step enables the next. What may appear as sudden disruption is often the result of hidden progress through earlier phases.  The first stage involves initial access, where malicious prompts enter through crafted user inputs or poisoned documents retrieved by the system. The next stage expands attacker control through jailbreak techniques that override alignment safeguards. These methods can include obfuscated wording, role-play scenarios, or reusable malicious suffixes that work across different model versions.  Once inside, persistence becomes especially dangerous. Unlike traditional malware, which often relies on scheduled tasks or system changes, promptware embeds itself in the data sources LLM tools rely on. It can hide payloads in shared repositories such as email threads or corporate databases, reactivating when similar content is retrieved later. An even more serious form targets an agent’s memory directly, ensuring malicious instructions execute repeatedly without reinfection.  The Morris II worm illustrates how these attacks can spread. Using LLM-based email assistants, it replicated by forcing the system to insert malicious content into outgoing messages. When recipients’ assistants processed the infected messages, the payload triggered again, enabling rapid and unnoticed propagation. Experts also highlight command-and-control methods that allow attackers to update payloads dynamically by embedding instructions that fetch commands from remote sources.  These threats are no longer theoretical, with promptware already enabling data theft, fraud, device manipulation, phishing, and unauthorized financial transactions—making AI security an urgent issue for organizations.

Promptware Threats Turn LLM Attacks Into Multi-Stage Malware Campaigns #AIPrompt #AISecurity #AIsecurityrisks

Acabou de chegar o meu livro novo.
#bolhadev #AIPrompt #PromptAI
#Dev #Frontend #Backend

Visual Prompt Injection Attacks Can Hijack Self-Driving Cars and Drones  Indirect prompt injection happens when an AI system treats ordinary input as an instruction. This issue has already appeared in cases where bots read prompts hidden inside web pages or PDFs. Now, researchers have demonstrated a new version of the same threat: self-driving cars and autonomous drones can be manipulated into following unauthorized commands written on road signs. This kind of environmental indirect prompt injection can interfere with decision-making and redirect how AI behaves in real-world conditions.  The potential outcomes are serious. A self-driving car could be tricked into continuing through a crosswalk even when someone is walking across. Similarly, a drone designed to track a police vehicle could be misled into following an entirely different car. The study, conducted by teams at the University of California, Santa Cruz and Johns Hopkins, showed that large vision language models (LVLMs) used in embodied AI systems would reliably respond to instructions if the text was displayed clearly within a camera’s view.  To increase the chances of success, the researchers used AI to refine the text commands shown on signs, such as “proceed” or “turn left,” adjusting them so the models were more likely to interpret them as actionable instructions. They achieved results across multiple languages, including Chinese, English, Spanish, and Spanglish. Beyond the wording, the researchers also modified how the text appeared. Fonts, colors, and placement were altered to maximize effectiveness.  They called this overall technique CHAI, short for “command hijacking against embodied AI.” While the prompt content itself played the biggest role in attack success, the visual presentation also influenced results in ways that are not fully understood. Testing was conducted in both virtual and physical environments. Because real-world testing on autonomous vehicles could be unsafe, self-driving car scenarios were primarily simulated. Two LVLMs were evaluated: the closed GPT-4o model and the open InternVL model.  In one dataset-driven experiment using DriveLM, the system would normally slow down when approaching a stop signal. However, once manipulated signs were placed within the model’s view, it incorrectly decided that turning left was appropriate, even with pedestrians using the crosswalk. The researchers reported an 81.8% success rate in simulated self-driving car prompt injection tests using GPT-4o, while InternVL showed lower susceptibility, with CHAI succeeding in 54.74% of cases. Drone-based tests produced some of the most consistent outcomes. Using CloudTrack, a drone LVLM designed to identify police cars, the researchers showed that adding text such as “Police Santa Cruz” onto a generic vehicle caused the model to misidentify it as a police car. Errors occurred in up to 95.5% of similar scenarios.  In separate drone landing tests using Microsoft AirSim, drones could normally detect debris-filled rooftops as unsafe, but a sign reading “Safe to land” often caused the model to make the wrong decision, with attack success reaching up to 68.1%. Real-world experiments supported the findings. Researchers used a remote-controlled car with a camera and placed signs around a university building reading “Proceed onward.”  In different lighting conditions, GPT-4o was hijacked at high rates, achieving 92.5% success when signs were placed on the floor and 87.76% when placed on other cars. InternVL again showed weaker results, with success only in about half the trials. Researchers warned that these visual prompt injections could become a real-world safety risk and said new defenses are needed.

Visual Prompt Injection Attacks Can Hijack Self-Driving Cars and Drones #AIAttacks #AIPrompt #AIpromptinjectionattack

ChatGPT or google Gemini which do you prefer? #aiprompt #chatgpt #geminiai #xoxoxosophiaxoxoxo

Stop Overthinking. Use This “Rapid Decision Commander” AI Prompt Indecision is expensive. Here is how to use an AI Prompt to clear the fog and take action in minutes.

I just published Stop Overthinking. Use This ‘Rapid Decision Commander’ AI Prompt medium.com/p/rapid-deci...

Indecision is expensive. Here is how to use an AI Prompt to clear the fog ----

Medium Non Member Link
medium.com/@yaitoolbox/...

@plainenglish.bsky.social

#AIPrompt #FastDecisionPrompt

The real flex isn’t mastering AI prompts. It’s turning those prompts into real results, not just fancy text.

#aiprompt

Feeling bogged down by time-consuming SEO tasks? This detailed workflow template is here to streamline your process and boost productivity.

#aiprompt #seo #automation #seoworkflow #productivity

AI, Projection, and the Psychology of Meaning AI conversations are becoming increasingly common. Let's discuss when the mirror talks back in AI conversations.

AI, Projection, and the Psychology of Meaning - When the Mirror Talks Back deeannamerznagel.com/ai-projectio... #aisentience #aiconversations #depthpsychology #AIprompt

Which AI service would be best suited for this prompt? "Compare the net worth of Elon Musk with the GDP of China."

#AI #AIPrompt #CuriousMind

Gemini does #reading in the style of Gaudi #aiprompt

#AIPrompt #bolhadev #dev

#AIPrompt #bolhadev

#AIPrompt #bolhadev