News for hackers. Stuff that matters.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by TeMPOraL on Friday May 16, 2025 @03:38AM (#44002723)
Missing in your description is that at least some of that work of "people spending hundreds of hours crafting workflows to get around deficiencies in models, posting tutorials about it, other people spending all the time to learn those workflows" is exactly what informed model developers about the major problems and what solutions seem most promising. All these workarounds are organically crowd-sourcing R&D, which is arguably one of the most impressive things about whole image generation space. The community around ComfyUI is pretty much a shapeless distributed research organization.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by latentsea on Sunday May 18, 2025 @06:58PM (#44024933)
You're 100% right. I definitely witnessed and picked up on that too. Good callout.