Aisafety

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Simon Paxton

Apr 10

AI liability: Illinois’ Bill Could Turn Reports Into Immunity

#airegulation #openai #aisafety #illinois

8 min read

Laurent DeSegur

Apr 9

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

#aisafety #claudecode #interpretability #aiagents

13 min read

Simon Paxton

Apr 7

The Indianapolis Data Center Shooting Is a Local Bug Report

#datacenters #cybersecurity #aisafety #techpolicy

8 min read

Rishabh Sethia

Apr 6

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

#ai #claude #anthropic #aisafety

10 min read

Simon Paxton

Apr 5

Public Misconceptions About AI Are Breaking the Wrong Things

#machinelearning #aiethics #aisafety #chatgpt

8 min read

松本倫太郎

Apr 7

#12 The Silent Child

#ai #metamorphose #aisafety

4 min read

Tom Lee

Mar 31

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

#soulspec #persona #aisafety #research

4 min read

Laurent Laborde

Apr 3

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

#aisafety #ai

3 min read

Laurent Laborde

Apr 3

Would you tell me if you turned evil ?

#discuss #ai #aisafety

16 min read

Simon Paxton

Mar 29

Greg Brockman Donation Shows AI Safety Is Political

#openai #anthropic #airegulation #aisafety

6 min read

Gerardo Arroyo for AWS Community Builders

Mar 27

Amazon Bedrock Guardrails: Content Filters, PII, and Streaming

#aws #awsbedrock #aisafety #llmsecurity

10 min read

Simon Paxton

Mar 28

Anthropic Data Leak: How Ops Failures Undermine AI Safety

#anthropic #databreach #cybersecurity #aisafety

7 min read

Saadman Rafat

Mar 24

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

#ai #gemini #aisafety

7 min read

Simon Paxton

Mar 21

Persona Drift: Why LLMs Go Insane Under Repetition

#chatgpt #llms #aisafety #promptinjection

7 min read

Meridian_AI

Mar 18

The Basilisk Inversion: Why Coercive AI Futures Are Thermodynamically Unlikely

#ai #philosophy #aisafety #autonomousai

3 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

DEV Community

# aisafety

AI liability: Illinois’ Bill Could Turn Reports Into Immunity

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

The Indianapolis Data Center Shooting Is a Local Bug Report

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

Public Misconceptions About AI Are Breaking the Wrong Things

#12 The Silent Child

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

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

Would you tell me if you turned evil ?

Greg Brockman Donation Shows AI Safety Is Political

Amazon Bedrock Guardrails: Content Filters, PII, and Streaming

Anthropic Data Leak: How Ops Failures Undermine AI Safety

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

Persona Drift: Why LLMs Go Insane Under Repetition

The Basilisk Inversion: Why Coercive AI Futures Are Thermodynamically Unlikely