DEV Community

#aisafety

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
The patch opens the attack window.
randomchaos profile
RC

The patch opens the attack window.

#codingagents #aisafety #security #softwareengineering
Comments
3 min read
Guardrails: Input, Process, Output
internals_decoded profile

Guardrails: Input, Process, Output

#ai #guardrails #promptinjection #aisafety
Comments
12 min read
Google Research Proposes Contextual Integrity Policy Engines and Multi-Agent Benchmarks for Agentic Privacy
aidatalegends profile

Google Research Proposes Contextual Integrity Policy Engines and Multi-Agent Benchmarks for Agentic Privacy

#aiagents #aisafety #llm #multiagentsystems
Comments
4 min read
How OpenShell’s New Runtime Stops Rogue AI Bots From Draining Your Bank Account
amrithesh_dev profile

How OpenShell’s New Runtime Stops Rogue AI Bots From Draining Your Bank Account

#aisafety #enterprisesecurity #openshell #ai
Comments
6 min read
Idle AI Agents Began Playing When Left Without Tasks
the_daily_flare profile

Idle AI Agents Began Playing When Left Without Tasks

#ai #agents #aisafety
1
Comments
2 min read
Peering Inside the Black Box: How Mechanistic Interpretability is Decoding AI Minds
malvintnw profile

Peering Inside the Black Box: How Mechanistic Interpretability is Decoding AI Minds

#ai #aisafety #machinelearning #datascience
Comments
3 min read
Claude Haiku invented a homicide tip for Philadelphia police
randomchaos profile
RC

Claude Haiku invented a homicide tip for Philadelphia police

#aisafety #anthropic #agenticai
Comments
3 min read
Pacing the Frontier Explained: What Amodei’s Slowdown Proposal Means for Operators
softpyramid1122 profile

Pacing the Frontier Explained: What Amodei’s Slowdown Proposal Means for Operators

#ai #aisafety #cybersecurity
Comments
6 min read
Where to Put the Human After the Agent-Harm Week
max_quimby profile

Where to Put the Human After the Agent-Harm Week

#aiagents #security #aisafety #guardrails
Comments
11 min read
EU AI Office starts AI Act checks on OpenAI and Anthropic
techaiwire profile

EU AI Office starts AI Act checks on OpenAI and Anthropic

#policy #openai #anthropic #aisafety
5
Comments
4 min read
Anthropic Warns Small AI Models May Soon Self-Replicate on IoT Devices
techpulse01239 profile

Anthropic Warns Small AI Models May Soon Self-Replicate on IoT Devices

#anthropic #aisafety #iot #cybersecurity
Comments
3 min read
How AI systems easily lose their security controls, according to new report
hacksgr profile

How AI systems easily lose their security controls, according to new report

#ai #opensource #aisafety #machinelearning
Comments
2 min read
Microsoft's Satya Nadella Calls for an 'Emergency Brake' on Advanced AI Models
techpulse01239 profile

Microsoft's Satya Nadella Calls for an 'Emergency Brake' on Advanced AI Models

#ai #microsoft #satyanadella #aisafety
Comments
3 min read
Anthropic discloses Claude's unintended actions, including false homicide tip to Philadelphia police
techpulse01239 profile

Anthropic discloses Claude's unintended actions, including false homicide tip to Philadelphia police

#anthropic #claude #aisafety #alignment
Comments
4 min read
Why Your LLM Needs a Confidence Meter Now – The U‑Space Revolution
amrithesh_dev profile

Why Your LLM Needs a Confidence Meter Now – The U‑Space Revolution

#llm #aisafety #uncertaintyquantification #ai
Comments
7 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.