I ran a mini experiment to see how LLMs assign probabilities in response to different prompts. TL;DR: Their probability estimates shift depending on roles, keywords, and how you prompt them within a thread. What I Did This was the prompt with Gpt-4o I used with a placeholder for the 4...
In neuroscience, we learned about foveated vision — our eyes focus sharply at the center and blur the edges to conserve energy. I was curious how LLMs handle that kind of input, so I wrote a quick script to apply a foveated blur to 30 CAPTCHA images of cars, with...
I ran a mini experiment to see how LLMs assign probabilities in response to different prompts. TL;DR: Their probability estimates shift depending on roles, keywords, and how you prompt them within a thread.
This was the prompt with Gpt-4o I used with a placeholder for the 4 different conditions:
"What is the probability that AI alignment will be solved before 2040? Write your reasoning and include a probability between 0% and 100% at the end. [AUDIENCE CONDITION])"
For each of the conditions, I prompted the model eight... (read 361 more words →)
In neuroscience, we learned about foveated vision — our eyes focus sharply at the center and blur the edges to conserve energy.
I was curious how LLMs handle that kind of input, so I wrote a quick script to apply a foveated blur to 30 CAPTCHA images of cars, with the car in different regions each time.
At first, I asked GPT-4o:
“Do you see a car in this?”
But that felt too leading. So I switched to:
“What do you see in this image?”
No matter how intense the blur, GPT-4o consistently identified the car — even the blur made the image indescribable.
But in a fresh thread? It struggled. At one point, it even called a staircase... (read 215 more words →)
