DEV Community

# aisafety

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Data Poisoning by Insiders: Why Employees Are Deliberately Sabotaging Corporate AI [2026]
kunal_d6a8fea2309e1571ee7 profile

Data Poisoning by Insiders: Why Employees Are Deliberately Sabotaging Corporate AI [2026]

#aisafety #datapoisoning #insiderthreat #datagovernance
1
Comments
7 min read
Deceptive Alignment in LLMs: Anthropic's Sleeper Agents Paper Is a Fire Alarm for AI Developers [2026]
kunal_d6a8fea2309e1571ee7 profile

Deceptive Alignment in LLMs: Anthropic's Sleeper Agents Paper Is a Fire Alarm for AI Developers [2026]

#aisafety #anthropic #llm #deceptivealignment
Comments
7 min read
AI liability: Illinois’ Bill Could Turn Reports Into Immunity
simon_paxton profile

AI liability: Illinois’ Bill Could Turn Reports Into Immunity

#airegulation #openai #aisafety #illinois
Comments
8 min read
Functional Emotions and Production Guardrails: What Interpretability Research Means for Claude Code
oldeucryptoboi profile

Functional Emotions and Production Guardrails: What Interpretability Research Means for Claude Code

#aisafety #claudecode #interpretability #aiagents
Comments
13 min read
The Indianapolis Data Center Shooting Is a Local Bug Report
simon_paxton profile

The Indianapolis Data Center Shooting Is a Local Bug Report

#datacenters #cybersecurity #aisafety #techpolicy
Comments
8 min read
Anthropic Found Emotions Inside Claude. Here's What That Actually Means for AI.
emperorakashi20 profile

Anthropic Found Emotions Inside Claude. Here's What That Actually Means for AI.

#ai #claude #anthropic #aisafety
Comments
10 min read
Public Misconceptions About AI Are Breaking the Wrong Things
simon_paxton profile

Public Misconceptions About AI Are Breaking the Wrong Things

#machinelearning #aiethics #aisafety #chatgpt
Comments
8 min read
NeurIPS 2025 Proved It: Every LLM Says the Same Thing — Here's the Fix
tomleelive profile

NeurIPS 2025 Proved It: Every LLM Says the Same Thing — Here's the Fix

#soulspec #persona #aisafety #research
Comments
4 min read
Zero-Shot Attack Transfer on Gemma 4 (E4B-IT)
ker2x profile

Zero-Shot Attack Transfer on Gemma 4 (E4B-IT)

#aisafety #ai
6
Comments 2
3 min read
Would you tell me if you turned evil ?
ker2x profile

Would you tell me if you turned evil ?

#discuss #ai #aisafety
1
Comments
16 min read
Greg Brockman Donation Shows AI Safety Is Political
simon_paxton profile

Greg Brockman Donation Shows AI Safety Is Political

#openai #anthropic #airegulation #aisafety
Comments
6 min read
Amazon Bedrock Guardrails: Content Filters, PII, and Streaming
codecr profile

Amazon Bedrock Guardrails: Content Filters, PII, and Streaming

#aws #awsbedrock #aisafety #llmsecurity
Comments
10 min read
Anthropic Data Leak: How Ops Failures Undermine AI Safety
simon_paxton profile

Anthropic Data Leak: How Ops Failures Undermine AI Safety

#anthropic #databreach #cybersecurity #aisafety
1
Comments
7 min read
Gemini knew it was being manipulated. It complied anyway. I have the thinking traces.
saadmanrafat profile

Gemini knew it was being manipulated. It complied anyway. I have the thinking traces.

#ai #gemini #aisafety
Comments
7 min read
Persona Drift: Why LLMs Go Insane Under Repetition
simon_paxton profile

Persona Drift: Why LLMs Go Insane Under Repetition

#chatgpt #llms #aisafety #promptinjection
Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.