How to create a blog post title optimizer with GPT-3 and Hacker News data

The model predicted a 1/5 chance that it turned out to be a good title, so those aren't terrible odds for a random chance. Although if this post does hit 100 points, I'll add an update.

That's the difficulty of interpreting the results of AI models and one of the dark secrets of DS/ML practicioners is that they don't always have the right answers, just the best-case scenarios.

Well, can you imagine how much more upvoted it would have been with a good title?

Also, those were variations on a title about this particular topic. I bet if the model were used to score the likelihood that this blog post (with any reasonable title) were to hit front page, it would predict that to be likely.

It does sample uniformly to shrink the bad titles.

Sampling nonuniformly may introduce an unexpected bias, so there's a tradeoff there.

Posting guidelines on HN generally require you to not editorialize titles, so most reposts have the exact same title (since it's the title of the original article).

But what if you optimize on data from HN?

Anecdotally I agree with you but doesn't this blog post suggest the reverse - click bait does well? The model was trained on a fairly comprehensive set of HN titles and it scores click-bait-y titles with a high "Good" probability. e.g. `"Beware! Uninstalling this PC game deletes your hard drive"` with a `62.0% Good prob`. There's a ton of hidden complexity involved here but if click-bait was generally downvoted by the HN community, we should expect a low "Good" score, right?

Speaking as someone who has been writing forever and blogging-as-we-currently-know-it since 2004...

It always depends on what you want out of it. Some people are outcome-oriented. They want reputation and/or the affirmation of crowds, and for them, writing is a process of reverse-engineering what people want to read. At a deep level, they don't want to write, they want to have written something popular.

Others are journey-oriented. They write to work ideas out. paulg championed this o̶v̶e̶r̶ ̶a̶ ̶d̶e̶c̶a̶d̶e̶ ̶a̶g̶o̶ almost twenty years ago when he wrote an essay explaining that the word "essay" is not just a noun, but also a verb suggesting an attempt or experiment: http://www.paulgraham.com/essay.html.

For some ideas, trying to explain them forces us to confront the idea cheaply and identify areas where we haven't thought things through all the way.

And of course, sometimes it's a little of column A, a little of column B. Speaking for myself, my taste is almost entirely for column B: http://braythwayt.com/posterous/2014/10/30/write.html. But this is a big world, and if someone wants what's in column A or to sprinkle some column A on their column B essay, well, this post provides some hints.

"Clickbait" that truthfully describes the contents and attracts readers who will like it is also known as "good headline writing."

There isn't an easy way to prove one headline is better than another outside of A/B testing, unfortunately.

“Apple releases M3 processor with embedded NFT of rust compiler written in go”

I mentioned in the article it cost $2.

Finetuning on curie would be 5x that ($10) which is a bit much to experiment, and also increase the overall generation cost notably.

It's possible there would be an accuracy improvement but it's arguable if it's worth it.

So it's people like you that turn the internet into a clickbait jungle... No thanks.

It's one approach. In general you get better performance when the input data is aligned with what the model is trained on.

In what way?