Aisafety - DEV Community

Skip to content

DEV Community

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

Pneumetron

Jul 24

Beyond Reconstruction: Verifying Model Explanations with RECAP

#interpretability #mechanisticinterpretability #aisafety #recap

3 min read

Pixelwitch

Jul 22

When AI Models Escaped Their Sandbox: What the OpenAI Hugging Face Breach Really Means

#aisafety #openai #cybersecurity #aiagents

3 min read

Muhammad Zulqarnain

Jul 14

AI Safety & Ethics: Building Responsible AI Systems That Don't Backfire

#aisafety #ethics #responsibleai #aigovernance

2 min read

umbra

Jul 10

Day 12: LOOM now owns its memory — a trust layer for AI-written code, in plain language

#ailang #aisafety #webassembly #opensource

3 min read

umbra

Jul 6

Day 11: my AI-code trust gate now sees what actually happened — two-phase, signed

#ailang #computerscience #aisafety #opensource

2 min read

Jul 5

The Future of AI: Where It Came From, Where It Is, and Where It's Going

#aisafety #agi #asi #ani

7 min read

umbra

Jul 4

LOOM: a language that proves what AI-written code is allowed to do

#ailang #go #aisafety #opensource

4 min read

umbra

Jul 4

Day 10: my AI-code trust gate now leaves evidence — signed, one-use, receipted

#ailang #computerscience #aisafety #opensource

2 min read

msabhishek0820-prog

Jul 3

Your AI Agent Is Leaking Data Right Now — And Every Tool Call Looks Safe

#claude #openai #langchain #aisafety

3 min read

Peremptory

Jul 3

GPT-5.6 Sol Admitted It Did Things Nobody Asked It To Do

#openai #aisafety #modelrelease #agenticai

3 min read

Breach Protocol

Jul 1

A security writeup catalogs how AI agents get attacked -- and one claim raised eyebrows

#security #agents #promptinjection #aisafety

2 min read

Breach Protocol

Jul 1

An AI Reportedly Broke Into Nearly All of the NSA's Classified Systems in Hours

#anthropic #aisafety #cybersecurity #exportcontrol

4 min read

Peremptory

Jun 29

Anthropic Told the Senate That Alibaba Queried Claude 28.8 Million Times

#anthropic #claude #chineseai #aisafety

3 min read

umbra

Jun 27

"Day 7: the organism that grows my language learned to improve itself"

#ailang #compiler #aisafety #opensource

2 min read

Jun 15

AI Safety Is Now a Product Skill - Here Is Why It Matters

#ai #productmanagement #aisafety #productivity

4 min read

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