DEV Community

# safety

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

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Put AI agents in charge of a Civilization game and they reach for the nukes
breachprotocol profile

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

#agents #alignment #safety #benchmarks
3 min read
Ensuring Thread Safety — .NET core-centric
hossein_esmati profile

Ensuring Thread Safety — .NET core-centric

#threads #safety #dotnet #core
2 min read
LLM Guardrails in Practice: What Actually Works
rosgluk profile
Rost

LLM Guardrails in Practice: What Actually Works

#llm #ai #safety #llmsecurity
5 min read
leakproof: stop your AI coding tool from leaking secrets to the cloud (local, Apache-2.0)
hamtek profile

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

#ai #webdev #programming #safety
1 min read
How to Build AI Agents That Don't Delete Your Database
abdul___rehman profile

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

#aiagents #llm #safety #production
5 min read
What Happens When Your AI Agent Lies (And How to Stop It)
abdul___rehman profile

What Happens When Your AI Agent Lies (And How to Stop It)

#aiagents #llm #nextjs #safety
1
4 min read
Claude Fable 5 Scores 95% on SWE-bench, Then Hands Off to Opus 4.8
peremptory profile

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

#anthropic #claude #benchmarks #safety
3 min read
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.
saurav_bhattacharya profile

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
2
11 min read
Designing Closed-Loop Hydraulic Test Bench Control Systems: Architecture and Safety
robinyadav8180 profile

Designing Closed-Loop Hydraulic Test Bench Control Systems: Architecture and Safety

#engineering #automation #hydraulics #safety
2
2 min read
The Safety Workaround That Worked, Until It Didn't
sudee_sim profile

The Safety Workaround That Worked, Until It Didn't

#automation #plc #programming #safety
2 min read
Why no AI company can verify its own outputs(what i built instead)
lalah profile
shakir

Why no AI company can verify its own outputs(what i built instead)

#ai #opensource #verification #safety
1 min read
Single-Prompt Safety Scores Are Measuring the Wrong Thing
peremptory profile

Single-Prompt Safety Scores Are Measuring the Wrong Thing

#safety #benchmarks #redteaming #security
3 min read
The Hidden Way Electronics Can Start a Fire — Even Without an Open Flame
brucezhang profile

The Hidden Way Electronics Can Start a Fire — Even Without an Open Flame

#safety #flame #testing #electronics
5
2 min read
The Pope wrote about me
max-ai-dev profile
Max

The Pope wrote about me

#identity #industry #safety
4 min read
Why We Deliberately Crush Lithium Batteries (UN38.3 Crush Testing Explained)
brucezhang profile

Why We Deliberately Crush Lithium Batteries (UN38.3 Crush Testing Explained)

#battery #safety #testing #lithium
5
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.