tylerrobinson
Joined 8 years ago
Joined 8 years ago
It sounds like the product is intended to help you avoid performance-related regressions, and argues that the risk of performance regressions will increase with AI writing more code. That seems plausible, but it's unclear how or why this product is superior to existing performance testing as part of your CI/CD pipeline.
Yeesh. I guess that makes one of us. Truly one of the more horrifying short stories I’ve read.
@shapiro500
No shade if so, I think it’s an awesome little toy.
> Like many parents, I found that standard bedtime stories didn't always capture their unique imagination. So, I built Lyra Kids (https://lyra.kids) to turn our nightly ritual into something more magical.
We have the standard template product pitch here (“Unlike our competitors, our product does XYZ”) but turned against _the entirety of children’s literature_.
You really think that many parents find “standard bedtime stories” insufficient?
Look, we have a couple of those books that use your kid’s name and a custom illustration that resembles them. They’re about as sophisticated as a Hallmark card and equally unrewarding. The kids get a kick out of it, but it’s a rare amusement and not actual interest. You don’t talk about the plot or the characters of a Mad Lib.
I’ll set aside my moral outrage and assume that you wanted to build this project no matter what and backed into the product positioning later, because the alternative is too depressing to consider.
Are you sharing any of the prompts you used to generate this? Even if not verbatim, I’m interested to know how much you’re driving versus the model. How much more prompt is there than, “look at this comment history and write 3 roasts that the HN crowd will find funny”?