Forem

# aisafety

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Why AI Chatbots Go Insane: Understanding the Assistant Axis and Persona Drift
claudiuspapirus profile

Why AI Chatbots Go Insane: Understanding the Assistant Axis and Persona Drift

#ai #machinelearning #aisafety #anthropic
Comments
2 min read
When Safety Becomes Control
Cover image for When Safety Becomes Control
rawveg profile

When Safety Becomes Control

#humanintheloop #aimanipulation #psychologicalcontrol #aisafety
Comments
23 min read
When One AI Designs Communication Protocols for Another
Cover image for When One AI Designs Communication Protocols for Another
mkraft-berlin profile

When One AI Designs Communication Protocols for Another

#discuss #ai #futureofai #aisafety
1
Comments
3 min read
I’m Not Building AI Demos. I’m Building AI Audits (ASDP + Slop Gates)
Cover image for I’m Not Building AI Demos. I’m Building AI Audits (ASDP + Slop Gates)
flamehaven01 profile

I’m Not Building AI Demos. I’m Building AI Audits (ASDP + Slop Gates)

#devops #mlops #governance #aisafety
Comments
3 min read
Semantic Field Risk Memo — On an Unmodeled High-Dimensional Risk in LLM-based Systems
yuer profile
yuer

Semantic Field Risk Memo — On an Unmodeled High-Dimensional Risk in LLM-based Systems

#semanticfield #llmrisk #aisafety #aigovernance
Comments
7 min read
Meta-DAG: Why AI Ethics Failed as Engineering — and What I Built Instead
alan_tsai_00dbd905e668f74 profile

Meta-DAG: Why AI Ethics Failed as Engineering — and What I Built Instead

#googleaiteamchallenge #aigovernance #aisafety #ai治理
Comments
2 min read
The Loop Changes Everything: Why Embodied AI Breaks Current Alignment Approaches
evoleinik profile

The Loop Changes Everything: Why Embodied AI Breaks Current Alignment Approaches

#aisafety #robotics #alignment #systemsarchitecture
Comments
5 min read
Stop Making AI Learn From Us
Cover image for Stop Making AI Learn From Us
rawveg profile

Stop Making AI Learn From Us

#humanintheloop #aialignment #biasamplification #aisafety
1
Comments
19 min read
Prompt Injection: The Breach We Can't Patch
Cover image for Prompt Injection: The Breach We Can't Patch
aiservices profile

Prompt Injection: The Breach We Can't Patch

#ai #llm #aisecurity #aisafety
Comments
3 min read
The Agent Control Plane: Why Intelligence Without Governance Is a Bug
mosiddi profile

The Agent Control Plane: Why Intelligence Without Governance Is a Bug

#agenticai #opensource #aisafety #aiarchitecture
Comments 1
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.