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.
Controversy Gate Second Model Check
apexgridtech profile

Controversy Gate Second Model Check

#ai #safety #opensource #architecture
Comments
2 min read
The Right to Be Forgotten Is Hard for AI: Why Deleting Your Data From a Model Isn’t a Delete Button
theaidownside profile

The Right to Be Forgotten Is Hard for AI: Why Deleting Your Data From a Model Isn’t a Delete Button

#privacy #airegulation #safety #llms
Comments
5 min read
When AI Refuses Perfectly Normal Requests
theaidownside profile

When AI Refuses Perfectly Normal Requests

#censorship #refusals #safety #ux
Comments
7 min read
Constitutional AI: os princĂ­pios Ă©ticos que tornam o Claude Ăşnico
andr_diasmoreiraprol_b profile

Constitutional AI: os princĂ­pios Ă©ticos que tornam o Claude Ăşnico

#claudeai #safety #anthropic #ai
Comments
3 min read
Claude Opus 4.6 Shows Why Old Models Need Patch Windows
reidmarlow profile

Claude Opus 4.6 Shows Why Old Models Need Patch Windows

#ai #safety #agents #devtools
6
Comments
5 min read
Could GPT-5.6 Sol Have a Dangerous Vulnerability?
giuliomarinelli profile

Could GPT-5.6 Sol Have a Dangerous Vulnerability?

#discuss #ai #machinelearning #safety
Comments
9 min read
Why Child Safety Tracking Should Never Be Paywalled
omarelhaitoum profile

Why Child Safety Tracking Should Never Be Paywalled

#family #privacy #safety #android
Comments
1 min read
“Safe AI for Teens” Needs a Recoverable Escalation Flow, Not One Generic Refusal
haaaaaley profile

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

#ux #ai #safety #productdesign
Comments
3 min read
Our AI Agent Failed 5 Times in One Day. Here is Why It Never Happened Again.
zwiserfit profile

Our AI Agent Failed 5 Times in One Day. Here is Why It Never Happened Again.

#opensource #ai #agents #safety
1
Comments 5
2 min read
The safety switch that doesn't actually work
breachprotocol profile

The safety switch that doesn't actually work

#interpretability #safety #sparseautoencoders
Comments
4 min read
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
Comments
3 min read
A big study finds AI more persuasive than professional human persuaders
breachprotocol profile

A big study finds AI more persuasive than professional human persuaders

#persuasion #safety #society #research
Comments
3 min read
Ensuring Thread Safety — .NET core-centric
hossein_esmati profile

Ensuring Thread Safety — .NET core-centric

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

LLM Guardrails in Practice: What Actually Works

#llm #ai #safety #llmsecurity
Comments
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
Comments
1 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.