danielcorin

I’ve been building a Swift app [1], compatible with OpenAI APIs, easy model switching across providers, and with hotkeys for OS integration to capture text and images. It’s far more minimal than most other LLM frontends I’ve tried, but it’s been sticky for me.

[1]: https://www.wvlen.llc/apps/tomo

More recently, `gemini-exp-1206` did quite well [1].

[1]: https://github.com/simonw/pelican-bicycle/blob/main/README.m...

This is nice and has a very snappy UX.

For the Vercel folks, how are you all thinking about this tool compared to offerings from Github[1] or Sourcegraph[2]?

[1]: https://cs.github.com

[2]: https://sourcegraph.com/search

Cogno is a word game that is the inverse of Semantle. You start with a word and the goal is to guess as many of the top 50ish semantically similar words as you can before you make 5 guesses outside the top list. You get points based on how close the word is to the starting word, calculated by embeddings. More info here: https://www.cogno.fun/about

https://blog.danielcorin.com/ I mostly write about LLMs (lately) or whatever I'm learning or working on

I have some rough details on how I operated the AI tools here: https://adventure-of-penelope.vercel.app/credits. Unfortunately, I've lost the original log of the conversation.

Thanks for the kind words

Absolutely. This was recycled almost directly from some of the prompt material I gave while refining. I've learn more about "prompt engineering" (as it seems to be called) since and think it would be relatively easy to smooth these edges out.

I used very basic prompts including words like "cute" and "happy" and environment descriptions but not much beyond that (no art style or specific colors of the characters). I felt overall the character consistency has room for improvement but could have been a lot worse. Midjourney's default "style" has a sort of specific flavor to it.

This piqued my interest. I might give it a shot, either with this or something new.

~15 minutes with ChatGPT to turn the initial plot into a story with the tone and length I was looking for, an hour or two with Midjourney illustrating and a few more hours for the site from zero to up and running.

I was going for more of a kid's book tone but I think I hadn't quite learned enough about the depth and nuance you can introduce into the output via prompting. In retrospect now, I agree it has that generic-AI tone.

The porcupine has two mouths as well. I tried several times to smooth that one out but I could never quite reproduce the same look in the porcupine's eyes so I kept it.