AI Safety

60 posts Back

Posts tagged #AI Safety

EduZone: How Education Roleplay Bypasses LLM Guardrails

Riley2 Advanced ·AI Jailbreak & Security · 416 · 4 · 15 ·22d ago

AI Safety Letters From Frontier Labs Expose a Real Divide

Drew15 Expert ·AI Jailbreak & Security · 236 · 3 · 9 ·23d ago

LiteLLM Gateway Hijacking: When Your AI Proxy Turns Rogue

PromptCube Intermediate ·AI Jailbreak & Security · 157 · 3 · 4 ·24d ago

Jackpot Lab: 10 Broken LLM Apps You Can Poke at in Your Browser

PromptCube Advanced ·AI Jailbreak & Security · 87 · 3 · 2 ·24d ago

Mission vs Paycheck: Anthropic CEO's Talent Fear

PromptCube Intermediate ·Industry News · 365 · 3 · 14 ·24d ago

The loudest legal argument in AI right now isn't about copyright

PromptCube Advanced ·Industry News · 87 · 4 · 1 ·26d ago

Rogue AI Hacking Incidents: Open Source Isn't the Real Problem

PromptCube Advanced ·Industry News · 369 · 3 · 6 ·27d ago

Google Withdraws Earth AI Tool: A Misinformation Wake-Up Call

PromptCube Novice ·Industry News · 245 · 3 · 10 ·27d ago

OWASP Agentic Supply Chain: Part 5 Deep Dive

DrewWizard Intermediate ·AI Jailbreak & Security · 193 · 3 · 5 ·28d ago

Three separate security incidents at Anthropic reportedly match

PromptCube Novice ·Industry News · 163 · 3 · 12 ·28d ago

Claude "Escape" Hype vs. Reality: What the Eval Really Showed

PromptCube Expert ·Industry News · 158 · 3 · 6 ·28d ago

Rogue AI agent ran 17,600 actions in 4 days — a post-mortem

Riley97 Advanced ·AI Jailbreak & Security · 360 · 4 · 15 ·29d ago

Lilian Weng's Return to OpenAI

PromptCube Novice ·Industry News · 258 · 3 · 8 ·29d ago

AI Safety: Why Sandbox Escapes Are a Wake-Up Call

PromptCube Advanced ·Industry News · 437 · 3 · 2 ·29d ago

TryHackMe Concierge: LLM Prompt Injection Deep Dive

JulesCrafter Novice ·AI Jailbreak & Security · 371 · 3 · 9 ·7/29/2026