samcollins

2 months agodiscuss

Thanks for the answers! Found it:

> All Project Gutenberg metadata are available digitally in the XML/RDF format. This is updated daily (other than the legacy format mentioned below). Please use one of these files as input to a database or other tools you may be developing, instead of crawling or roboting the website.

And strongly consider a donation! (My addition)

https://www.gutenberg.org/ebooks/offline_catalogs.html#the-p...

samcollins

2 months agodiscuss

Very cool! Do you have a recommended way for an agent to see an index of the books and epub links?

(I can’t quite tell if that’s an egregious abuse of the site or you’re perfectly fine to share without human eye balls hitting your www?)

samcollins

2 months agodiscuss

OP here. It took me an afternoon to try different methods and test the limits. But now we know how it works it’s very fast to create new ones:

1. Prompt to make SVG - review in browser, iterate.

2. Prompt to write image prompt - review in editor, refine

3. Send to Gemini, get image

So maybe 5-10 mins.

I don’t know how to use Blender.

Also this method can be done over WhatsApp/telegram which is another plus over Blender type approach.

samcollins

2 months agodiscuss

TLDR: use SVG to outline image correctly first, then send that image with your text prompt to get Gemini 3.0 Pro to render with correct numbers and text

samcollins

2 months agodiscuss

I found a simple technique to get reliable text and numbers in AI generated images.

I’m surprised the image models aren’t already doing this, so wanted to share since I’m finding this so useful

samcollins

3 months agodiscuss

Why do you say that? I thought this pattern was well established, or are you aware of known issues with it?

samcollins

4 months agodiscuss

Yep, I suspect this is the rationale/driver too.

samcollins

4 months agodiscuss

The business driver I assume is not lock-in on UX (as some say here) but the additional signal Anthropic gets when using their harness vs a 3P one. It makes sense to discount the price if that signal helps you improve your models, but that discount makes no sense if the user is running your model in another harness and you just get regular API usage signal.

samcollins

7 months agodiscuss

Nice! I made a similar thing but the html for the text editor fits in a data uri, so it can be a bookmark or new tab page for taking quick notes

https://gist.github.com/smcllns/8b727361ce4cf55cbc017faaefbb...

samcollins

9 months agodiscuss

Re 19, I made this with an iOS Shortcut a few weeks ago

  > A minimal voice assistant for my Apple Watch. I have lots of questions that are too complicated for Siri but not for ChatGPT. The responses should just be a few words long.

Use Dictate Text action to take voice as input, pass the text to OpenAI API as the user message with this as the system prompt:

“CRITICAL: Your response will only be shown in an iOS push notification or on a watch screen, so answer concisely in <150 characters. Do not use markdown formatting - responses are rendered as plain text. Do use minimalist, stylish yet effective vocabulary and punctuation.

CRITICAL: The user can not respond so do not ask a question back. Answer the prompt in one shot and if necessary, declare assumptions about the users questions so you could answer it in one shot, while making it possible for the user user to repeat ask with more clarity if your assumptions were not right.”

It works well. The biggest annoyance is it takes about 5-20s to return a response, though I love that it’s nearly instantaneous to send my question (don’t need to wait for any apps to open etc)

samcollins

Submissions

Using “underdrawings” for accurate text and numbers

comments