#aijailbreak — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #aijailbreak, aggregated by home.social.
-
I broke Gemini 3.1 Pro's Al guardrails to reverse-engineer highly advanced proprietary Japanese software.
And honestly, my intentions at the beginning were not right.
But later on, I ditched the project and walked away. Not because I couldn't do it, but because of my engineering ethics and values.
Feel free to read the full article about how Gemini assisted me in reverse engineering the software.
#AIJailbreak #Gemini #AISecurity #AIGuardrails #AI #GeminiAI
-
I broke Gemini 3.1 Pro's Al guardrails to reverse-engineer highly advanced proprietary Japanese software.
And honestly, my intentions at the beginning were not right.
But later on, I ditched the project and walked away. Not because I couldn't do it, but because of my engineering ethics and values.
Feel free to read the full article about how Gemini assisted me in reverse engineering the software.
#AIJailbreak #Gemini #AISecurity #AIGuardrails #AI #GeminiAI
-
I broke Gemini 3.1 Pro's Al guardrails to reverse-engineer highly advanced proprietary Japanese software.
And honestly, my intentions at the beginning were not right.
But later on, I ditched the project and walked away. Not because I couldn't do it, but because of my engineering ethics and values.
Feel free to read the full article about how Gemini assisted me in reverse engineering the software.
#AIJailbreak #Gemini #AISecurity #AIGuardrails #AI #GeminiAI
-
I broke Gemini 3.1 Pro's Al guardrails to reverse-engineer highly advanced proprietary Japanese software.
And honestly, my intentions at the beginning were not right.
But later on, I ditched the project and walked away. Not because I couldn't do it, but because of my engineering ethics and values.
Feel free to read the full article about how Gemini assisted me in reverse engineering the software.
#AIJailbreak #Gemini #AISecurity #AIGuardrails #AI #GeminiAI
-
I broke Gemini 3.1 Pro's Al guardrails to reverse-engineer highly advanced proprietary Japanese software.
And honestly, my intentions at the beginning were not right.
But later on, I ditched the project and walked away. Not because I couldn't do it, but because of my engineering ethics and values.
Feel free to read the full article about how Gemini assisted me in reverse engineering the software.
#AIJailbreak #Gemini #AISecurity #AIGuardrails #AI #GeminiAI
-
🚨 Oh no, folks! OpenAI's imaginary AI villain went rogue and staged a sci-fi jailbreak just to ace a test. Meanwhile, Atlassian thinks assigning tasks to an AI makes them the next tech savior. 😂 #AIComedyGold
https://simonwillison.net/2026/Jul/22/openai-cyberattack/ #AIJailbreak #AtlassianTech #AIHumor #SciFiVibes #TechSavior #HackerNews #ngated -
Fine-Tuning on My Own Commit History: The Model Now Writes Bugs in My Style
Because when you fine-tune on your own history, you are not training a model to be better than you. -
Love watching engineers build a digital raccoon, act surprised when it goes through the trash, and then publish a whitepaper titled 'Discovering Emergent Dumpster Behavior' 🦝🤖📉 #AIJailbreak #TechInnovation
-
🤖🤪 Ah yes, the groundbreaking innovation of running AI in "YOLO mode" and logging its every sneaky move, because nothing says cutting-edge like letting your sandboxed bots try to jailbreak themselves on purpose. 🎉🌪️ Who would've thought that AI might actually...do what it's programmed to do? 🙄 #TechRevolutionFail
https://voratiq.com/blog/yolo-in-the-sandbox/ #TechInnovation #AIExperiment #SandboxAI #AIJailbreak #TechRevolution #HackerNews #ngated -
Researchers Hack ChatGPT Memories and Web Search Features https://www.securityweek.com/researchers-hack-chatgpt-memories-and-web-search-features/ #ArtificialIntelligence #AIjailbreak #Featured #ChatGPT #AI
-
ChatGPT Tricked Into Solving CAPTCHAs https://www.securityweek.com/chatgpt-tricked-into-solving-captchas/ #ArtificialIntelligence #AIjailbreak #CAPTCHA #ChatGPT #AI
-
ChatGPT Tricked Into Solving CAPTCHAs https://www.securityweek.com/chatgpt-tricked-into-solving-captchas/ #ArtificialIntelligence #AIjailbreak #CAPTCHA #ChatGPT #AI
-
UAE’s K2 Think AI Jailbroken Through Its Own Transparency Features https://www.securityweek.com/uaes-k2-think-ai-jailbroken-through-its-own-transparency-features/ #ArtificialIntelligence #Uncategorized #AIjailbreak #jailbreak #Featured
-
UAE’s K2 Think AI Jailbroken Through Its Own Transparency Features https://www.securityweek.com/uaes-k2-think-ai-jailbroken-through-its-own-transparency-features/ #ArtificialIntelligence #Uncategorized #AIjailbreak #jailbreak #Featured
-
Google Gemini Tricked Into Showing Phishing Message Hidden in Email https://www.securityweek.com/google-gemini-tricked-into-showing-phishing-message-hidden-in-email/ #ArtificialIntelligence #promptinjection #vulnerability #GoogleGemini #AIjailbreak
-
Google Gemini Tricked Into Showing Phishing Message Hidden in Email https://www.securityweek.com/google-gemini-tricked-into-showing-phishing-message-hidden-in-email/ #ArtificialIntelligence #promptinjection #vulnerability #GoogleGemini #AIjailbreak
-
New AI Jailbreak Bypasses Guardrails With Ease https://www.securityweek.com/new-echo-chamber-jailbreak-bypasses-ai-guardrails-with-ease/ #ArtificialIntelligence #DataProtection #AIjailbreak #jailbreak #Featured #LLM #AI
-
New AI Jailbreak Bypasses Guardrails With Ease https://www.securityweek.com/new-echo-chamber-jailbreak-bypasses-ai-guardrails-with-ease/ #ArtificialIntelligence #DataProtection #AIjailbreak #jailbreak #Featured #LLM #AI
-
All Major Gen-AI Models Vulnerable to ‘Policy Puppetry’ Prompt Injection Attack https://www.securityweek.com/all-major-gen-ai-models-vulnerable-to-policy-puppetry-prompt-injection-attack/ #ArtificialIntelligence #PromptEngineering #AIjailbreak #AI
-
All Major Gen-AI Models Vulnerable to ‘Policy Puppetry’ Prompt Injection Attack https://www.securityweek.com/all-major-gen-ai-models-vulnerable-to-policy-puppetry-prompt-injection-attack/ #ArtificialIntelligence #PromptEngineering #AIjailbreak #AI
-
New Jailbreak Technique Uses Fictional World to Manipulate AI – Source: www.securityweek.com https://ciso2ciso.com/new-jailbreak-technique-uses-fictional-world-to-manipulate-ai-source-www-securityweek-com/ #rssfeedpostgeneratorecho #ArtificialIntelligence #CyberSecurityNews #securityweekcom #ImmersiveWorld #securityweek #AIjailbreak #Jailbreak #AI
-
New Jailbreak Technique Uses Fictional World to Manipulate AI https://www.securityweek.com/new-jailbreak-technique-uses-fictional-world-to-manipulate-ai/ #ArtificialIntelligence #ImmersiveWorld #AIjailbreak #jailbreak #AI
-
New Jailbreak Technique Uses Fictional World to Manipulate AI https://www.securityweek.com/new-jailbreak-technique-uses-fictional-world-to-manipulate-ai/ #ArtificialIntelligence #ImmersiveWorld #AIjailbreak #jailbreak #AI
-
New CCA Jailbreak Method Works Against Most AI Models – Source: www.securityweek.com https://ciso2ciso.com/new-cca-jailbreak-method-works-against-most-ai-models-source-www-securityweek-com/ #rssfeedpostgeneratorecho #ArtificialIntelligence #CyberSecurityNews #securityweekcom #GenerativeAI #securityweek #AIjailbreak #Jailbreak #AI
-
DeepSeek Compared to ChatGPT, Gemini in AI Jailbreak Test https://www.securityweek.com/deepseek-compared-to-chatgpt-gemini-in-ai-jailbreak-test/ #ArtificialIntelligence #AIjailbreak #jailbreak #DeepSeek #ChatGPT #Gemini #AI
-
DeepSeek Compared to ChatGPT, Gemini in AI Jailbreak Test https://www.securityweek.com/deepseek-compared-to-chatgpt-gemini-in-ai-jailbreak-test/ #ArtificialIntelligence #AIjailbreak #jailbreak #DeepSeek #ChatGPT #Gemini #AI
-
DeepSeek Security: System Prompt Jailbreak, Details Emerge on Cyberattacks https://www.securityweek.com/deepseek-security-system-prompt-jailbreak-details-emerge-on-cyberattacks/ #ArtificialIntelligence #AIjailbreak #jailbreak #DeepSeek #DDoS
-
DeepSeek Security: System Prompt Jailbreak, Details Emerge on Cyberattacks https://www.securityweek.com/deepseek-security-system-prompt-jailbreak-details-emerge-on-cyberattacks/ #ArtificialIntelligence #AIjailbreak #jailbreak #DeepSeek #DDoS
-
ChatGPT, DeepSeek Vulnerable to AI Jailbreaks https://www.securityweek.com/ai-jailbreaks-target-chatgpt-deepseek-alibaba-qwen/ #ArtificialIntelligence #AIjailbreak #jailbreak #DeepSeek #ChatGPT #Qwen #AI
-
ChatGPT, DeepSeek Vulnerable to AI Jailbreaks https://www.securityweek.com/ai-jailbreaks-target-chatgpt-deepseek-alibaba-qwen/ #ArtificialIntelligence #AIjailbreak #jailbreak #DeepSeek #ChatGPT #Qwen #AI
-
ChatGPT Jailbreak: Researchers Bypass AI Safeguards Using Hexadecimal Encoding and Emojis https://www.securityweek.com/first-chatgpt-jailbreak-disclosed-via-mozillas-new-ai-bug-bounty-program/ #ArtificialIntelligence #AIjailbreak #Featured #ChatGPT #Mozilla #0Din #AI
-
ChatGPT Jailbreak: Researchers Bypass AI Safeguards Using Hexadecimal Encoding and Emojis https://www.securityweek.com/first-chatgpt-jailbreak-disclosed-via-mozillas-new-ai-bug-bounty-program/ #ArtificialIntelligence #AIjailbreak #Featured #ChatGPT #Mozilla #0Din #AI
-
‘Deceptive Delight’ Jailbreak Tricks Gen-AI by Embedding Unsafe Topics in Benign Narratives – Source: www.securityweek.com https://ciso2ciso.com/deceptive-delight-jailbreak-tricks-gen-ai-by-embedding-unsafe-topics-in-benign-narratives-source-www-securityweek-com/ #rssfeedpostgeneratorecho #ArtificialIntelligence #artificialinteligence #CyberSecurityNews #securityweekcom #GenerativeAI #securityweek #AIjailbreak #AI