How I used GPT-3 to hit Hacker News front page 5 times in 3 weeks

Re:How I used GPT-3 to hit Hacker News front page 5 times in... by minimaxir on Wednesday October 28, 2020 @05:18PM (#24924253)

The title is very misleading: GPT-3 generated the titles, but as usual, they were manually curated on the "picked the title I liked the most" criteria.

There's more to getting to the front of Hacker News than just a good title (although it helps); ironically this framing undersells the writing capabilities of the author by attributing success to the AI only.

There are ways in theory for AI models to generate "better" titles, which is something I'm actively researching (rough example: https://github.com/minimaxir/gpt-3-experiments/tree/master/e...).

[ Parent | on HN ]

Re:How I used GPT-3 to hit Hacker News front page 5 times in... by dunkeylim on Wednesday October 28, 2020 @10:39PM (#24926518)

It doesn’t seem misleading to me, they explicitly said “How I used GPT-3”, not “How GPT-3 generated”. (Unless they edited the title)

[ Parent | on HN ]

Re:How I used GPT-3 to hit Hacker News front page 5 times in... by sullyj3 on Thursday October 29, 2020 @12:33AM (#24927246)

Sometimes people infer things that aren't strictly speaking logically implied. That doesn't make it not misleading, if it reliably causes people to make those inferences.

[ Parent | on HN ]

Re:How I used GPT-3 to hit Hacker News front page 5 times in... by minimaxir on Wednesday October 28, 2020 @11:18PM (#24926798)

It's implying a direct causal effect to getting to the front page, which given the article argument is not well supported.

[ Parent | on HN ]

Re:How I used GPT-3 to hit Hacker News front page 5 times in... by simonebrunozzi on Friday October 30, 2020 @11:30AM (#24943266)

You are correct, but I would still agree that it is misleading to some extent.

[ Parent | on HN ]