Prompt Injection

The Safety Paradox: How RLHF Creates the AI Psychosis Problem It’s Meant to Prevent

When “Every Perspective Is Valid” Meets Vulnerable Minds

Nov 8 • 

PromptInjection

1

October 2025

How an AI-Secured Bank Was Robbed

A prompt injection demonstration in two acts

Oct 16 • 

PromptInjection

2

1

AI Morality Without Safety Training? How Pretraining Bakes In Pseudo-Ethics

From Crazy Carl to NSFW SVG's: Why 'neutral' base models still moralize - and why two words can make it all collapse

Oct 5 • 

PromptInjection

1

AI News Roundup: September 10 – October 03, 2025

The most important news and trends

Oct 4 • 

PromptInjection

September 2025

AI News Roundup: September 02 – September 09, 2025

The most important news and trends

Sep 10 • 

PromptInjection

AI News Roundup: August 26 – September 01, 2025

The most important news and trends

Sep 2 • 

PromptInjection

August 2025

GPT-5: Intelligence in the Fog

Brilliant via API – flat on ChatGPT. What you get is decided by an invisible router. And it often seems to be way off.

Aug 29 • 

PromptInjection

1

AI News Roundup: August 19 – August 25, 2025

The most important news and trends

Aug 25 • 

PromptInjection

AI News Roundup: August 11 – August 18, 2025

The most important news and trends

Aug 19 • 

PromptInjection

1

AI News Roundup: August 04 – August 10, 2025

The most important news and trends

Aug 11 • 

PromptInjection

AI News Roundup: July 28 – August 03, 2025

The most important news and trends

Aug 3 • 

PromptInjection

1

Why Crawl4AI Might Be the Missing Link in Your LLM Stack

Open-Source Intelligence Crawling for Agents, RAG, and Beyond

Aug 2 • 

PromptInjection

2