Please tell me I wasn't the only one to have clicked on the link, viewed the page and assumed I must have misclicked and was still on HN...

That’s amazing, some of those articles are priceless bits of HN satire.

Yes! I've also noticed that GPT-3.5 and GPT-4 have somewhat different senses of humor. GPT-3.5 tends to lean more towards absurdism — sometimes it's so bad that it's actually good, but that's not always the case. So, I use both for generating headlines.

However, GPT-3.5 often struggles to generate coherent comment threads, so I use GPT-4 for that, which does the job pretty well.

For images, I simply ask LLM to include a prompt in the img alt tag, and then I call the DALL-E API to generate JPEGs. But honestly, DALL-E isn't great; it would be much better to use StableDiffusion or Midjourney, but I'm too lazy to integrate them (does Midjourney even have a public API?)

If you want to see the prompts, here is the code: https://github.com/crackernews/crackernews.github.io

Thank you for sharing this.

This particular headline cracks me up: "Javascript: the Secret Language of Dolphins?"

This is hilarious, great work! I guess we can add satire to the list of industries being disrupted by AI.

Argh, some articles don't fit in a single LLM response and get cut. Maybe add a fake paywall for a more realistic experience!