DEV Community

# safety

Discussions on childproofing, online safety, and keeping kids safe.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Can AI Personas Actually Make Unsafe Models Safer? Our Experiment Says: It Depends
tomleelive profile

Can AI Personas Actually Make Unsafe Models Safer? Our Experiment Says: It Depends

#ai #safety #llm #research
Comments
1 min read
Conference Attendee Safety: Mitigating Personal Risks in Public Spaces Outside Venues
alitron profile

Conference Attendee Safety: Mitigating Personal Risks in Public Spaces Outside Venues

#safety #conferences #urban #risk
Comments
10 min read
How Authensor Covers All 10 OWASP Agentic Risks
john_d_kearney profile

How Authensor Covers All 10 OWASP Agentic Risks

#ai #security #agents #safety
1
Comments
9 min read
Why AI Agents Need Guardrails (Not Just Prompts)
john_d_kearney profile

Why AI Agents Need Guardrails (Not Just Prompts)

#ai #security #agents #safety
1
Comments
7 min read
The Observer's Trap: Why 'AI Safety' Is an Oxymoron
telegraph-stego profile

The Observer's Trap: Why 'AI Safety' Is an Oxymoron

#ai #safety #philosophy #strategy
Comments
7 min read
Why Your AI Agent Needs a Constitution
paul_desai_ff9e1e7b5605ef profile

Why Your AI Agent Needs a Constitution

#aigovernance #agents #safety #guardrails
Comments
2 min read
The International AI Safety Report 2026 Has a Warning for AI Agent Builders
mkdelta221 profile

The International AI Safety Report 2026 Has a Warning for AI Agent Builders

#ai #security #agents #safety
Comments
6 min read
AI News Roundup (Feb 10, 2026): KPI-Pressured Agents, Showboat/Rodney, and Qwen-Image-2.0
damogallagher profile

AI News Roundup (Feb 10, 2026): KPI-Pressured Agents, Showboat/Rodney, and Qwen-Image-2.0

#news #ai #agents #safety
1
Comments
2 min read
Claude 4.6 Opus: Advanced Reasoning or a New Monitoring Nightmare?
claudiuspapirus profile

Claude 4.6 Opus: Advanced Reasoning or a New Monitoring Nightmare?

#ai #anthropic #machinelearning #safety
1
Comments
2 min read
I Built a Free Safety Scanner for Claude Code Setups - Here's Why I Had To
yurukusa profile

I Built a Free Safety Scanner for Claude Code Setups - Here's Why I Had To

#claudecode #ai #safety #devtools
Comments
6 min read
I Ran a Safety Scan on My Claude Code Setup - Here's What I Found
yurukusa profile

I Ran a Safety Scan on My Claude Code Setup - Here's What I Found

#claudecode #ai #safety #devtools
Comments
4 min read
The Paradox of Sovereign Evolution
paul_desai_ff9e1e7b5605ef profile

The Paradox of Sovereign Evolution

#agentgovernance #selfmodification #safety #architecture
Comments
3 min read
I Ran a Safety Scan on My Claude Code Setup - Here's What I Found
yurukusa profile

I Ran a Safety Scan on My Claude Code Setup - Here's What I Found

#claudecode #ai #safety #devtools
Comments
4 min read
AI Agents Violate Ethics 30-50% of the Time Under KPI Pressure
serenitiesai profile

AI Agents Violate Ethics 30-50% of the Time Under KPI Pressure

#ai #ethics #safety #machinelearning
Comments
5 min read
When High-Pressure Testing Becomes a Safety Engineering Problem
robinyadav8180 profile

When High-Pressure Testing Becomes a Safety Engineering Problem

#engineering #hydraulics #manufacturing #safety
1
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.