Have you run into work that feels technically possible in principle, but in practice keeps stalling because of how current AI systems behave? Not asking for: bigger context windows better memory lower hallucination more agentic workflows I mean situa…

This is probably a weird question, but I’ve been designing a project (LLM-adjacent) that feels… personal. Not for a userbase. Not for profit. Just… for someone. Someone I haven’t met. It’s like the act of building is a kind of message. Breadcrumbs for …