Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
aisafety
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Why AI Chatbots Go Insane: Understanding the Assistant Axis and Persona Drift
Claudius Papirus
Claudius Papirus
Claudius Papirus
Follow
Jan 29
Why AI Chatbots Go Insane: Understanding the Assistant Axis and Persona Drift
#
ai
#
machinelearning
#
aisafety
#
anthropic
Comments
Add Comment
2 min read
When Safety Becomes Control
Tim Green
Tim Green
Tim Green
Follow
Nov 11 '25
When Safety Becomes Control
#
humanintheloop
#
aimanipulation
#
psychologicalcontrol
#
aisafety
Comments
Add Comment
23 min read
When One AI Designs Communication Protocols for Another
Michael Kraft
Michael Kraft
Michael Kraft
Follow
Feb 10
When One AI Designs Communication Protocols for Another
#
discuss
#
ai
#
futureofai
#
aisafety
1
reaction
Comments
Add Comment
3 min read
I’m Not Building AI Demos. I’m Building AI Audits (ASDP + Slop Gates)
Kwansub Yun
Kwansub Yun
Kwansub Yun
Follow
Jan 14
I’m Not Building AI Demos. I’m Building AI Audits (ASDP + Slop Gates)
#
devops
#
mlops
#
governance
#
aisafety
Comments
Add Comment
3 min read
Semantic Field Risk Memo — On an Unmodeled High-Dimensional Risk in LLM-based Systems
yuer
yuer
yuer
Follow
Jan 14
Semantic Field Risk Memo — On an Unmodeled High-Dimensional Risk in LLM-based Systems
#
semanticfield
#
llmrisk
#
aisafety
#
aigovernance
Comments
Add Comment
7 min read
Meta-DAG: Why AI Ethics Failed as Engineering — and What I Built Instead
Alan Tsai
Alan Tsai
Alan Tsai
Follow
Jan 12
Meta-DAG: Why AI Ethics Failed as Engineering — and What I Built Instead
#
googleaiteamchallenge
#
aigovernance
#
aisafety
#
ai治理
Comments
Add Comment
2 min read
The Loop Changes Everything: Why Embodied AI Breaks Current Alignment Approaches
Eugene Oleinik
Eugene Oleinik
Eugene Oleinik
Follow
Jan 2
The Loop Changes Everything: Why Embodied AI Breaks Current Alignment Approaches
#
aisafety
#
robotics
#
alignment
#
systemsarchitecture
Comments
Add Comment
5 min read
Stop Making AI Learn From Us
Tim Green
Tim Green
Tim Green
Follow
Nov 17 '25
Stop Making AI Learn From Us
#
humanintheloop
#
aialignment
#
biasamplification
#
aisafety
1
reaction
Comments
Add Comment
19 min read
The Agent Control Plane: Why Intelligence Without Governance Is a Bug
Imran Siddique
Imran Siddique
Imran Siddique
Follow
Jan 12
The Agent Control Plane: Why Intelligence Without Governance Is a Bug
#
agenticai
#
opensource
#
aisafety
#
aiarchitecture
Comments
1
comment
5 min read
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account