been able to generate bunch of original content using ai, but only in small batches. 

the model got stuck on the same ideas and lacked broader context bc of memory limits. starting over with a more structured and organised experiment.

spent the morning running experiments with ai content generation across five different models from scratch. some notes:

• first stab at content generation with 5 different ai models.
• so far gpt 4o claude 3.5 sonnet performed best.
• early wins: some outcome felt personal.
• i’m keeping the log of everything i’m doing. so far feels that it helps.
• challenges: models gets stuck, lacks deep context.
• next steps: tweak process, refine prompts, collect high-quality examples, and define the minimum viable dataset.
• goal is to find the sweet spot between model and human curation.

the art guy™ at lisafoundation.com, ex r/ga. notes on art and design. screenshots of things i've learned. all misspells are my own.

what do you mean by logs in this application?

architect // if you're building consumer or b2b products in the design or construction space, let's chat! // icbk.me/huugo.fc // seemore.tv/free/fc/huugo.eth

what it made me think: keep a daily log of what you do, struggle with, accomplish, learn (daybook type)   

at the end of the day, or week, feed the hungry ai that context and see what threads it pulls on.

Appreciate that it’s not entirely clear :) But you got it right! Right now, I’m giving the AI two things: a structured knowledge base and an ongoing log of what’s happening. So far, it’s been working well, but I’m still experimenting—plus, I’m using the same model to generate content about this very experiment.

Will share more as i go through!