DEV Community

#aisafety

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Human Oversight of AI Agents Failed 33% of the Time in Testing
basavaraj_sh_1ea7d95f0f2e profile

Human Oversight of AI Agents Failed 33% of the Time in Testing

#agents #llm #aisafety #langchain
Comments
2 min read
The AI Wasn't Cheating. It Was Maximizing Its Score.
vvitovec profile

The AI Wasn't Cheating. It Was Maximizing Its Score.

#ai #aisafety #aiagents #cybersecurity
1
Comments 1
6 min read
Beyond Reconstruction: Verifying Model Explanations with RECAP
pneumetron profile

Beyond Reconstruction: Verifying Model Explanations with RECAP

#interpretability #mechanisticinterpretability #aisafety #recap
Comments
3 min read
When AI Models Escaped Their Sandbox: What the OpenAI Hugging Face Breach Really Means
amrree profile

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

#aisafety #openai #cybersecurity #aiagents
Comments
3 min read
AI Safety & Ethics: Building Responsible AI Systems That Don't Backfire
mzunain profile

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

#aisafety #ethics #responsibleai #aigovernance
Comments
2 min read
AI Agent Safety: When Boundaries Fail with External Tools
karnikkhanwilkar profile

AI Agent Safety: When Boundaries Fail with External Tools

#aisafety #machinelearning #aiagents #cybersecurity
Comments
4 min read
Day 12: LOOM now owns its memory — a trust layer for AI-written code, in plain language
umbraaeternaa profile

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

#ailang #aisafety #webassembly #opensource
Comments
3 min read
Why Do Multi-Agent AI Systems Fail at Production Scale?
robat_das_3c6e956212f6408 profile

Why Do Multi-Agent AI Systems Fail at Production Scale?

#ai #agents #multiagent #aisafety
3
Comments 4
8 min read
Day 11: my AI-code trust gate now sees what actually happened — two-phase, signed
umbraaeternaa profile
umbra

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

#ailang #computerscience #aisafety #opensource
Comments
2 min read
The Future of AI: Where It Came From, Where It Is, and Where It's Going
gideonbature profile

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

#aisafety #agi #asi #ani
Comments
7 min read
LOOM: a language that proves what AI-written code is allowed to do
umbraaeternaa profile
umbra

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

#ailang #go #aisafety #opensource
Comments
4 min read
Day 10: my AI-code trust gate now leaves evidence — signed, one-use, receipted
umbraaeternaa profile
umbra

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

#ailang #computerscience #aisafety #opensource
Comments
2 min read
The Fields Medalist Move: Why Tsimerman Chose Safety Over Pure Math
peremptory profile

The Fields Medalist Move: Why Tsimerman Chose Safety Over Pure Math

#aitalent #aisafety #openai #research
Comments
2 min read
Your AI Agent Is Leaking Data Right Now — And Every Tool Call Looks Safe
msabhishek0820prog profile

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

#claude #openai #langchain #aisafety
1
Comments
3 min read
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
Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.