AI Jailbreak & Security 87 posts

Sort:

AI Jailbreak & Security — All Posts

Qwen 3.

Cameron9Advanced· 247 · 3 · 1 ·8/16/2026 AI Jailbreak & Security AI Safety LLM Security

Stop hunting for "magic words" to unlock LLM intelligence

NightPandaExpert· 90 · 4 · 0 ·8/15/2026 AI Jailbreak & Security AI Safety LLM Security

Why are we still treating AI alignment like a coat of paint

KaiDevExpert· 517 · 4 · 9 ·8/14/2026 AI Jailbreak & Security AI Safety LLM Security

ProbGuard can spot a jailbreak in just ten tokens

DrewCoderNovice· 321 · 3 · 15 ·8/13/2026 AI Jailbreak & Security AI Safety LLM Security

Can we actually steal the "hidden" thoughts of a frontier LLM?

IndieFounderIntermediate· 537 · 4 · 1 ·8/12/2026 AI Jailbreak & Security AI Safety LLM Security

Claude Code auto mode is now the default for Pro and Team users

CameronOwlExpert· 537 · 3 · 5 ·8/11/2026 AI Jailbreak & Security AI Safety LLM Security

Can we stop just randomly mixing safety data into LLM

Morgan80Advanced· 400 · 3 · 7 ·8/10/2026 AI Jailbreak & Security AI Safety LLM Security

Can Item Response Theory actually fix the mess that is LLM

AlexHackerExpert· 90 · 3 · 5 ·8/9/2026 AI Jailbreak & Security AI Safety LLM Security

PIMiner can crack Gemini-2.5-Pro with a 76% success rate

NovaOwlIntermediate· 547 · 4 · 13 ·8/8/2026 AI Jailbreak & Security AI Safety LLM Security

Can we actually trust an MLLM to ignore a TV commercial that

产品经理大熊Advanced· 429 · 3 · 14 ·8/8/2026 AI Jailbreak & Security AI Safety LLM Security

Changing a sentence to the past tense shouldn't theoretically

NovaGuruAdvanced· 436 · 4 · 11 ·8/7/2026 AI Jailbreak & Security AI Safety LLM Security

Why are we still pretending that LLM guardrails are an actual

DeepWhizIntermediate· 185 · 4 · 13 ·8/7/2026 AI Jailbreak & Security AI Safety LLM Security

DelusionEval: Why LLM Context Windows Might Be Dangerous

Leo37Novice· 468 · 3 · 15 ·8/6/2026 AI Jailbreak & Security AI Safety LLM Security

Claude Opus Jailbreak: Testing 3-Word Bypass Logic

Alex17Advanced· 321 · 4 · 8 ·8/6/2026 AI Jailbreak & Security AI Safety LLM Security

EduZone: How Education Roleplay Bypasses LLM Guardrails

Riley2Advanced· 416 · 4 · 15 ·8/5/2026 AI Jailbreak & Security AI Safety LLM Security

‹1 2 3 4 5 6 ›

Join our Telegram