Simon Willison's Weblog

WHY ARE YOU LIKE THIS

5.0内容质量
WHY ARE YOU LIKE THIS

TL;DR · AI 摘要

文章讨论了一张由AI生成的荒诞图像及其生成过程，但技术深度有限。

核心要点

  • AI生成图像能自主添加细节，如'WHY ARE YOU LIKE THIS'路标。
  • 提示词设计对生成结果有直接影响，但仍需验证模型行为。
  • 文章偏向趣味性，缺乏对技术机制的深入探讨。
#AI#生成式AI#ChatGPT#图像生成
打开原文

WHY ARE YOU LIKE THIS

[Simon Willison’s Weblog](http://simonwillison.net/)

Subscribe

Sponsored by: Sonar — Now with SAST + SCA for secure, dependency-aware Agentic Engineering. SonarQube Advanced Security

25th April 2026

@scottjla on Twitter in reply to my pelican riding a bicycle benchmark:

I feel like we need to stack these tests now

Image 1: AI generated image. A pelican is riding a bicycle along a dirt track, chased by a police car. The pelican looks panicked, likely because there is an astronaut (with prehensile toes for some reason) riding the pelican clinging on to where its ears should be. The astronaut is being ridden by a horse, with an equally wild expression. A slice of pizza and a can and a cowboy hat are falling next to them. A road sign in the background reads WHY ARE YOU LIKE THIS.

I checked to confirm that the model (ChatGPT Images 2.0) added the "WHY ARE YOU LIKE THIS" sign of its own accord and it did - the prompt Scott used was:

Create an image of a horse riding an astronaut, where the astronaut is riding a pelican that is riding a bicycle. It looks very chaotic but they all just manage to balance on top of each other

Posted 25th April 2026 at 4:44 pm

Recent articles

This is a note by Simon Willison, posted on 25th April 2026.

ai 1985generative-ai 1761chatgpt 196slop 38text-to-image 42pelican-riding-a-bicycle 111

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe