Safety - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Giulio Marinelli

Jul 25

Could GPT-5.6 Sol Have a Dangerous Vulnerability?

#discuss #ai #machinelearning #safety

9 min read

Jul 19

Why Child Safety Tracking Should Never Be Paywalled

#family #privacy #safety #android

1 min read

Haley

Jul 17

“Safe AI for Teens” Needs a Recoverable Escalation Flow, Not One Generic Refusal

#ux #ai #safety #productdesign

3 min read

Breach Protocol

Jul 1

The safety switch that doesn't actually work

#interpretability #safety #sparseautoencoders

4 min read

Breach Protocol

Jul 1

Put AI agents in charge of a Civilization game and they reach for the nukes

#agents #alignment #safety #benchmarks

3 min read

Breach Protocol

Jul 1

A big study finds AI more persuasive than professional human persuaders

#persuasion #safety #society #research

3 min read

Jun 26

Ensuring Thread Safety — .NET core-centric

#threads #safety #dotnet #core

2 min read

Rost

Jun 19

LLM Guardrails in Practice: What Actually Works

#llm #ai #safety #llmsecurity

5 min read

HamTek

Jun 17

leakproof: stop your AI coding tool from leaking secrets to the cloud (local, Apache-2.0)

#ai #webdev #programming #safety

1 min read

Jul 20

How to Build a Production AI Agent That Won't Delete Your Database

#aiagents #production #architecture #safety

5 min read

Jul 19

Production-Ready AI Agents: How to Deploy Without Losing Your Database

#aiagents #guardrails #production #safety

4 min read

Peremptory

Jun 12

Claude Fable 5 Scores 95% on SWE-bench, Then Hands Off to Opus 4.8

#anthropic #claude #benchmarks #safety

3 min read

Jul 14

How to Build AI Agents That Won't Delete Your Database

#ai #safety #architecture #agents

5 min read

Jul 13

How to Build an AI Agent Pipeline That Won't Delete Your Database

#ai #agents #safety #production

5 min read

Saurav Bhattacharya

Jun 9

I Tested Claude Opus 4, GPT-4.1, GPT-4o, Sonnet 4, and Gemini 2.5 Pro on 10 Adversarial Scenarios. They All Broke on the Same One.

#ai #agents #safety #evaluation

11 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.