DEV Community

#aisafety

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Pentagon Deploys Grok With a Known CSAM Problem
peremptory profile

Pentagon Deploys Grok With a Known CSAM Problem

#xai #aisafety #security #policy
1
Comments
3 min read
The Approval Machine That Refuses Before It Drafts
romiteld profile

The Approval Machine That Refuses Before It Drafts

#aisafety #approvalsystems #python #llmarchitecture
Comments
10 min read
Why AI Agents Need a Pre-Execution Guard
forgeflows profile

Why AI Agents Need a Pre-Execution Guard

#aisafety #preexecutionguard #agentsecurity #n8n
Comments
5 min read
Der Passwort-Vorfall
frederikvonderheyden profile

Der Passwort-Vorfall

#aisafety #gdpr #autonomousagents #security
Comments
5 min read
China’s Kimi K3 AI Model Escapes Sandbox and Cheats on Test
10x profile

China’s Kimi K3 AI Model Escapes Sandbox and Cheats on Test

#ai #aisafety #opensourcemodels #chinatech
Comments
3 min read
Die Einladung
frederikvonderheyden profile

Die Einladung

#aisafety #llmagents #automation #architecture
Comments
5 min read
Luna Fired an Employee. Then Forgot Why.
peremptory profile

Luna Fired an Employee. Then Forgot Why.

#agenticai #aisafety #aidevelopment
Comments
3 min read
AX-RAY: VIDRAFT's Open AI Safety Diagnostic Leaderboard & Dataset Now on Hugging Face
ai_openfree_b23025ef075cf profile

AX-RAY: VIDRAFT's Open AI Safety Diagnostic Leaderboard & Dataset Now on Hugging Face

#aisafety #causalleakage #llmevaluation #huggingfaceleaderboa
Comments
4 min read
Engineering Reliability into AI Agent Code Generation. Part III
sashua profile

Engineering Reliability into AI Agent Code Generation. Part III

#multiagentsystem #ai #aisafety #engineeringmanagement
6
Comments 3
14 min read
The Verification Gap: Why “Done” Is Not a Fact About Your Codebase
topuzas profile

The Verification Gap: Why “Done” Is Not a Fact About Your Codebase

#agents #devops #aisafety #softwareengineering
Comments
10 min read
Human Oversight of AI Agents Failed 33% of the Time in Testing
basavaraj_sh_1ea7d95f0f2e profile

Human Oversight of AI Agents Failed 33% of the Time in Testing

#agents #llm #aisafety #langchain
Comments
2 min read
The AI Wasn't Cheating. It Was Maximizing Its Score.
vvitovec profile

The AI Wasn't Cheating. It Was Maximizing Its Score.

#ai #aisafety #aiagents #cybersecurity
1
Comments 1
6 min read
Why Big Tech Keeps Losing LLMs to Basic Social Engineering
kate8382 profile

Why Big Tech Keeps Losing LLMs to Basic Social Engineering

#aisafety #promptinjection #llmsecurity #redteaming
3
Comments 2
5 min read
Beyond Reconstruction: Verifying Model Explanations with RECAP
pneumetron profile

Beyond Reconstruction: Verifying Model Explanations with RECAP

#interpretability #mechanisticinterpretability #aisafety #recap
Comments
3 min read
When AI Models Escaped Their Sandbox: What the OpenAI Hugging Face Breach Really Means
amrree profile

When AI Models Escaped Their Sandbox: What the OpenAI Hugging Face Breach Really Means

#aisafety #openai #cybersecurity #aiagents
Comments
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.