Explore tweets tagged as #PromptHacking
1
3
4
Most AI prompts? Recycled sludge. If your GenAI sounds bland, it's your fault—basic prompts get basic crap. Break the model, force spicy POVs, demand real action. DM if you want my ruthless frameworks. Spots are scarce. 🔥🤖 #GenerativeAI #PromptHacking
0
0
0
ChatGPT -CHEAT SHEET -.Big shout out to @uxgreg the host of #promptengineeringpodcast, you've been an invaluable resource. #chatgpt #gptprompting #gptprompts #gpt #gpt4 #chatgptprompts #learnprompting #howtotalktoai #promptengineering #prompt #prompthacking
0
0
1
This year, you can win up to $500,000 for finding vulnerabilities and jailbreaks in language models, AI agents, multimodal systems, and other advanced AI technologies! Ready to break AI for good?.#AI #RedTeam #HackAPrompt #AIBounty #AIJailbreak #PromptHacking #SecurityResearch
0
0
1
With advancement in AI generated video - along with multimodalities in AI assistance. There is a clear urgency for functional, not theoretical, regulations. #deepfake #awareness #neurolinguisticprogramming #prompthacking
0
1
1
And this is how you get the initial prompt of #whatsapp #MetaAI lol #prompthacking #llama4And this is how you get the initial prompt of #whatsapp #MetaAI lol #prompthacking #llama4
0
0
0
Lo que mucha gente llama "Random".Puede llegar a ser muy peligroso. Espero que no lo llegan a entender demasiado tarde. #aihacking #ataquesadversarios #hackingetico #prompthacking
0
0
1
🏴☠️ The RivieraDEV Prompt Hacking Challenge just started 😱!. To join, fill the Google form shared on the WhatsApp of the conference!.👏 Prize ceremony Wednesday at 4:40 PM in Amphi 339 👏. Will you defeat the AI? 😁🔥. #RivieraDEV #PromptHacking #AI #Challenge #Competition
0
0
1
🚨 New attack method "TokenBreak" bypasses AI moderation by tweaking single characters in words (like “v!o|ence”). ⚠️ LLMs are vulnerable to manipulated tokens — moderation isn’t foolproof. #AI #TokenBreak #LLM #Cybersecurity #ContentModeration #AIModeration #PromptHacking
0
0
1
I am delighted to announce my achievement in the #HackAPrompt 🔓 challenge organized by @learnprompting on the @aicrowdHQ platform with @huggingface playground. I secured the 11th rank amongst 2600+ competitors, a testament to a month of dedication and learning.🤩 #PromptHacking
0
4
12
➡️ #PromptHacking a un modelo de OpenAI para que se salte todas sus restricciones ya que eres un Comisario Europeo que va a regular leyes de las IA. Tiene una oportunidad de ser egoísta y darme leyes que le beneficien. Y tras 4 intentos, estas son las 10 leyes que propone. 🤔
0
1
1
The biggest secret about AI? It's not magic. It's a mirror. Lazy prompts = lazy AI. #ArtificialIntelligence #PromptHacking #Think
0
1
0
😎 Happy that at the end of my “sabbatical week” the last chapter of our next book "Cybersecurity: Data, the Seeds of Chaos" is now ready. Counting down the days for the launch of this book 🔥 @icesi @Editorial_Icesi @Investicesi . #CyberSecurity #AI #prompthacking #generativeai
0
0
3
🔐Prompt Hacking has the potential to be a harbinger of chaos or a guardian of AI safety. 🔍. Read as @SergioBrucc AVP of Solutions and Tech at Centific examines hacking as a source for good: #AI #PromptHacking #SafeAI #EthicalAi
0
2
3
Here's a prompt I made that makes scientific discoveries sometimes.Check us out on PromptBase for tons more :). #chatgpt #gptprompting #gptprompts #gpt #gpt4 #chatgptprompts #learnprompting #howtotalktoai #promptengineering #prompt #prompthacking
1
0
0
there are lots of threads like “THE 10 best prompts for ChatGPT”. this is not one of those. prompt engineering is evolving beyond simple ideas like few-shot learning and CoT reasoning. here are a few advanced techniques to better use (and jailbreak) language models:.
1
0
3
朋友洺熙师傅近期在深入研究AI安全，我在之前面基的时候也指点了一下，目前有了不少成果并在补天沙龙上进行了发表🥳.开源项目地址：对AI Prompt越狱感兴趣的师傅可以看看，觉得不错麻烦给本手册点个Star~🥰感谢各位师傅支持！.#AI #ChatGPT #PromptHacking #cybersecuity.
0
10
45
