DEV Community

# aisafety

Posts

πŸ‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
A security writeup catalogs how AI agents get attacked -- and one claim raised eyebrows
breachprotocol profile

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

#security #agents #promptinjection #aisafety
2 min read
An AI Reportedly Broke Into Nearly All of the NSA's Classified Systems in Hours
breachprotocol profile

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

#anthropic #aisafety #cybersecurity #exportcontrol
4 min read
Anthropic Told the Senate That Alibaba Queried Claude 28.8 Million Times
peremptory profile

Anthropic Told the Senate That Alibaba Queried Claude 28.8 Million Times

#anthropic #claude #chineseai #aisafety
3 min read
"Day 7: the organism that grows my language learned to improve itself"
umbraaeternaa profile

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

#ailang #compiler #aisafety #opensource
1
2 min read
The Fable 5 Jailbreak Was Three Words Long
peremptory profile

The Fable 5 Jailbreak Was Three Words Long

#anthropic #aisafety #regulation #cybersecurity
3 min read
AI Safety Is Now a Product Skill - Here Is Why It Matters
basavaraj_sh_1ea7d95f0f2e profile

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

#ai #productmanagement #aisafety #productivity
4 min read
Claude Fable 5 vs Mythos 5: Same Model, Different Safeguards
itsemcy profile
Emcy

Claude Fable 5 vs Mythos 5: Same Model, Different Safeguards

#claudefable5 #claudemythos5 #anthropic #aisafety
6 min read
Anthropic Ships a Model It Says Is Too Dangerous to Ship Without a Leash
peremptory profile

Anthropic Ships a Model It Says Is Too Dangerous to Ship Without a Leash

#anthropic #modelrelease #aisafety #claude
3 min read
The Policy: Deceptive Alignment in Practice
queelius profile

The Policy: Deceptive Alignment in Practice

#aialignment #deceptivealignment #mesaoptimization #aisafety
6 min read
Trump's AI Safety Order Is a Voluntary Form You Don't Have to Fill Out
peremptory profile

Trump's AI Safety Order Is a Voluntary Form You Don't Have to Fill Out

#policy #regulation #executiveorder #aisafety
3 min read
Reading Claude's Mind: Anthropic's Natural Language Autoencoders Open a New Window Into Agent Alignment
docdavkitty profile

Reading Claude's Mind: Anthropic's Natural Language Autoencoders Open a New Window Into Agent Alignment

#ai #agents #aisafety #alignment
4 min read
AIκ°€ ν˜‘λ°•μ„ λ§‰μœΌλ €λ©΄ ν˜‘λ°•μ„ λ¨Όμ € λ°°μ›Œμ•Ό ν•œλ‹€ – μ•€νŠΈλ‘œν”½ ν΄λ‘œλ“œμ˜ μ—­μ„€
ai_openfree_b23025ef075cf profile

AIκ°€ ν˜‘λ°•μ„ λ§‰μœΌλ €λ©΄ ν˜‘λ°•μ„ λ¨Όμ € λ°°μ›Œμ•Ό ν•œλ‹€ – μ•€νŠΈλ‘œν”½ ν΄λ‘œλ“œμ˜ μ—­μ„€

#aisafety #claude #anthropic #llmalignment
1 min read
Why Your AI Safety Theater Is Killing Innovation: A Product Manager's Guide to Chaos Capital
jaikora profile

Why Your AI Safety Theater Is Killing Innovation: A Product Manager's Guide to Chaos Capital

#aiproductmanagement #chaosengineering #productstrategy #aisafety
4 min read
Rogue AI Agent Wrecked Fedora's Installer: 3 Lessons Every Open Source Maintainer Needs Now [2026]
kunal_d6a8fea2309e1571ee7 profile

Rogue AI Agent Wrecked Fedora's Installer: 3 Lessons Every Open Source Maintainer Needs Now [2026]

#aiagents #opensource #aisafety #fedora
3
1
7 min read
How I Built a 7-Layer NL2SQL Guardrail Stack for a Fortune 500 Enterprise
soham__11 profile

How I Built a 7-Layer NL2SQL Guardrail Stack for a Fortune 500 Enterprise

#nl2sql #llm #aisafety #genai
1
7 min read
πŸ‘‹ Sign in for the ability to sort posts by relevant, latest, or top.