3d • General discussion
AI hallucinations work like an optical illusion
Best mental model I've got for hallucinations, straight from the clip.
Show your brain part of an image and it fills in the rest. That's what the LLM does.
Your brain doesn't ask permission. It completes the picture and hands you a whole image, even though half of it was a guess. Language models do the same thing with facts. They fill in what they think should be there, and that filled-in piece can be something that never existed.
Once you see it as pattern-completion instead of lookup, the made-up citations and confident wrong dates stop being surprising. They're the same mechanism working exactly as built.
What's a hallucination you've caught that looked totally real at first?
0
0 comments
AI hallucinations work like an optical illusion
powered by
skool.com/blueprint-automation-systems-2678
Build your own AI operating system to run your business, one module a week. Real prompts, real files. No code, no hype. Free for now.
Suggested communities
Powered by