AI Jailbreak & Security

10 posts Back

Posts tagged #AI Jailbreak & Security

Multi-Agent Safety: The "Pipeline Effect" is a misleading metric

toolcalling Beginner ·AI Jailbreak & Security · 255 · 3 · 0 ·7h ago

Simulating Real-World Deployment to Predict Model Misalignment

humanfeedback Expert ·AI Jailbreak & Security · 567 · 4 · 0 ·7h ago

6,000 failed attempts and a Google account suspension later

softwhere Novice ·AI Jailbreak & Security · 379 · 4 · 0 ·17h ago

Autonomous LLM agents are moving from "helpful assistants" to

residualconn Beginner ·AI Jailbreak & Security · 121 · 3 · 0 ·19h ago

Anthropic's user-targeted prompt injection experiments

asyncawait Beginner ·AI Jailbreak & Security · 412 · 3 · 0 ·21h ago

The Myth of the Perfect AI Guardrail

chainofthought Beginner ·AI Jailbreak & Security · 115 · 4 · 0 ·1d ago

Running Local Math Kernels on Consumer GPUs

vcfunded82 Beginner ·AI Models · 57 · 3 · 0 ·1d ago

Mapping Resumes to Pokemon via Semantic Embeddings

decodingwave30 Beginner ·AI Models · 493 · 3 · 0 ·1d ago

Visualizing the internal workspace of LLMs

profsorry Beginner ·AI Models · 233 · 5 · 0 ·2d ago

LLM security is a never-ending boss fight

postdocai46 Beginner ·AI Jailbreak & Security · 444 · 3 · 0 ·2d ago