What’s the most common hallucination you've seen from an LLM?
For me, it’s when you ask, “How do I do X in Y app or software?”
For me, it’s when you ask, “How do I do X in Y app or software?”
Sometimes it just makes up steps that aren’t in the official documentation. Even worse, it sometimes pulls instructions from similar software and presents them as if they’re correct.
Enjoyed this? Subscribe for more.
Practical insights on AI, growth, and independent learning. No spam.
More in AI Agents
Hot Take: Vibe Coding Won't Replace Software Engineers
Here, I share my journey from a strong believer to a skeptic.
"How do I know if an AI agent skill is safe or malicious?"
I have been hearing this question very often recently. So I thought why not write about it.
20 FAQs on AEO, GEO and the New SEO
Marketers, search has changed. AI is rewriting the rules. If you're not adapting, you're disappearing.
Your AI agent will get prompt injected sooner or later, because it is easier than most people thought.
Most people think prompt injection needs a carefully crafted adversarial prompt by an experienced hacker. It does not. Someone who understands how LLMs work ...
Your OpenClaw Agent Is One Message Away from Getting Hacked
I gave a talk yesterday on OpenClaw security, at the largest OpenClaw event at Amazon Web Services (AWS), with 400 audience, organized by OpenClaw Singapore....
What Is Loop Engineering? Why Is It Trending? And Why Loops Are Not New
Loop engineering is everywhere right now. It is the practice of designing the system that prompts an AI agent, instead of prompting it yourself. Addy Osmani,...
Hot Take: Vibe Coding Won't Replace Software Engineers
Here, I share my journey from a strong believer to a skeptic.
20 FAQs on AEO, GEO and the New SEO
Marketers, search has changed. AI is rewriting the rules. If you're not adapting, you're disappearing.
Your OpenClaw Agent Is One Message Away from Getting Hacked
I gave a talk yesterday on OpenClaw security, at the largest OpenClaw event at Amazon Web Services (AWS), with 400 audience, organized by OpenClaw Singapore....
"How do I know if an AI agent skill is safe or malicious?"
I have been hearing this question very often recently. So I thought why not write about it.
Your AI agent will get prompt injected sooner or later, because it is easier than most people thought.
Most people think prompt injection needs a carefully crafted adversarial prompt by an experienced hacker. It does not. Someone who understands how LLMs work ...
What Is Loop Engineering? Why Is It Trending? And Why Loops Are Not New
Loop engineering is everywhere right now. It is the practice of designing the system that prompts an AI agent, instead of prompting it yourself. Addy Osmani,...