Building “A Young Lady's Illustrated Primer” (2011) | Hacker News Reader

Building “A Young Lady's Illustrated Primer” (2011)

proto-knowledge.blogspot.com

19 pointsctoth12 comments

I believe, with technology such as Stable Diffusion and LLaMa, "A Young Lady's Illustrated Primer" is more possible than ever.

Wasn't a core point of that story that only the primer backed and guided by a single invested & nurturing adult had the intended effect? The two that were driven programmatically failed to achieve the project's goals.

I am quite skeptic about that effect.

When a ractor's voice reaches the child, it is changed completely. Only some pattern remain here and there.

And Miranda just read words from a screen without ever touching or seeing Nell. She didn't even do anything on her own accord.

So, I am quite skeptic.

The book was quite clear that Nell intuited the presence of a caring entity on the other end of the scenes. She was even able to determine sometimes whether or not it was present in a specific interaction, though she didn't have a clear model for what she was sensing or why it would be sometimes absent.

What are you skeptical about? How the scenario in the book would play out in real life? I mean it's sci fi we don't have nanotech either. But the text of the novel itself is very clear about the value/necessity of the nurturing actor. If you have another way to interpret the text I'm open to hearing it but the author makes it pretty unambiguous imo.

I'm actually surprised someone hasn't tried making it yet.

Hahah. We did, but we were a few years too early for many parts of it. The Global Learning XPRIZE was a $15M challenge to build basically this: tablet software that could let kids without access to schools or teachers teach themselves.

We (Learn Leap Fly) were a semi-finalist in that competition. We bet heavily on AI, but again, were a few years early (Note the constraints of the problem said that the devices were NOT connected to the internet, which makes things still challenging today)

We were also a semi finalist (round 3) in the AI XPRIZE (with the same tech).

We’ve thought about whether to resurrect the core ideas and give it another go. For that we need partners. Education isn’t the most lucrative of fields, it turns out.

That said, anyone who wants to go down this path, send me a note. I’m happy to talk nerdity on this topic all day, be it AI, literacy education, pedagogy or grand challenges!

pretty much there with llama running locally, a few tweaks and we are good to go, drop in to my low rent gonzo AI lab twitch.tv/m88t and I can explain how we could do it...

Don't forget the beautiful illustrations in the book.

We can use Stable Diffusion. Huggingface's Diffusers library do a good job in running some versions locally really well.

thanks for the local tip, is it this, https://huggingface.co/blog/stable_diffusion ? Right now, aside from loading models etc, once it's running, you can disconnect the internet plus all open source :)

Slightly tangential.

Just like "alignment" of LLMs, the ideology this hypothetical book teaches will have huge controversy.

When Hackworth in the book tells the Judge/Dr. X that he will tweak the book so that it teaches them ideology more aligned towards the Celestial Kingdom's values, I immediately thought the things the American Conservatives, Leftists, and the C_CP will try to put in this.

I am interested in this, too.

Send me an email.

Kahn Academy is: https://www.khanacademy.org/khan-labs

Reply on news.ycombinator.com