HughParry

Use https://prosopo.io/ and it'll be easier :)

people are a bit happier here to have an argument and then get on with their lives though

Looks awesome!

How does it handle taking instruction about things like what stack to use?

E.g. if I'm building a new prototype, I personally would want to build with Tailwind, but lots of people think Tailwind is evil and prefer prototyping with <other_css_thing_they_like>

Also curious to hear what you think of the quality of the output code. My experiences with LLMs doing frontend code has been a pretty mixed bag personally

The danger is that we rely almost entirely on Google to solve this.

The monopoly they have as a search engine means there is effectively sole responsibility on them to maintain a usable internet.

I genuinely feel sorry for the people that now have to figure out how search engines work in a world where anybody can generate reams of passable (albeit not unique) content in minutes.

I've got a 20 year old set of their books in the basement. It's got facts which were wrong at the time of writing.

At the end of the day it's just a single centralised source

Demo looks very slick.

How far off being able to integrate into a CICD pipe is this? I'd love if this could trigger off a pr, then block merging since it wasn't sure how to execute some regular user flow (even if that were due to it not understanding how it could perform an action, since this maybe means my flow doesn't make sense).

We don't currently have this functionality, though if there's demand for non JS CAPTCHA products we'll definitely spec it out and build it.

If you want to request features/chat about any special requirements you have for a CAPTCHA, feel free to pop an email to dev@prosopo.io

Newest KPI is number of KPIs per month (lower is better). Lets circle back to that discussion later in our OKR chat this Friday