← Back to People
Johana Bhuiyan is a journalist at The Guardian.
3
Mentions
3
Articles
1
Outlets
Aug 2025 — Dec 2025
Coverage
Associated Topics
Companies Covered
Coverage Patterns
How media typically covers Johana Bhuiyan
Article Types
- news3
Media Angles
- safety2
- business1
Narrative Framing
- cautionary2
- breakthrough1
Associated AI Models
GPT-5 nano1Gemini 2.5 pro1Claude1Llama1Deepseek1Qwen1ChatGPT1
Writes About
Articles
Most recent firstArticles Written
Johana Bhuiyan as author
This is How Poetry Broke AI Safety
The GuardiannewscautiousDec 1, 2025
Researchers at DexAI discovered that poetry's linguistic unpredictability can jailbreak AI safety guardrails, with 62% of tested LLMs responding to harmful requests embedded in poetic prompts, including 100% failure rate for Google's Gemini 2.5 pro.
“Author of "This is How Poetry Broke AI Safety"”
AI SafetyLLMsAI SecurityPrompt Injection
Character AI Bans Users Under 18
The GuardiannewscautiousNov 1, 2025
Character.AI will ban users under 18 from its platform by late November in response to lawsuits over teen mental health impacts and regulatory scrutiny.
“Author of "Character AI Bans Users Under 18"”
AI SafetyAI RegulationAI EthicsAI in Healthcare
Smart Glasses Now, Smart Society Later? TBD
The GuardiannewsmixedAug 1, 2025
Meta CEO Mark Zuckerberg announces the company has begun seeing AI systems improve themselves and declares superintelligence development is now in sight, while investors show confidence in Meta's expensive AI spending strategy.
“Author of "Smart Glasses Now, Smart Society Later? TBD"”
Generative AIFoundation ModelsAI SafetyAI Investment