News for hackers. Stuff that matters.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by derwiki on Friday May 16, 2025 @12:11AM (#44001775)
The “go back and try the prompt again” is the workflow I’d like to see a UX improvement on. Outside of the vibe coding “accept all” path, reverse traversing is a fairly manual process.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by baq on Friday May 16, 2025 @01:57AM (#44002228)
Cursor has checkpoints for this but I feel I’ve never used them properly; easier to reject all and reprint. I keep chats short.
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by johnsmith1840 on Saturday May 17, 2025 @05:43PM (#44017208)
I don't think you will realistically.

Having full control over inputs and if something goes wrong starting a new chat with either narrower scope or clearer instructions is basically AGI level work.

There is nobody but a human for now that can determine how bad an LLM actually screwed up its logic train.

But maybe you mean pure UI?

I could forsee something like a new context creation button that gives a nice UI of what to bring over and what to ditch from the UI as pretty nice.

Maybe like a git diff looking method? Drop this paragraph bring this function by just simple clicks would be pretty slick!

I deffinetly see a future of better cross chat context connections and information being powerful. Basically git but for every conversation and cpde generated for a project.

Would be crazy hard but also crazy powerful.

If my startups blows up I might try something like that!