News for hackers. Stuff that matters.

A comment on The Unreasonable Effectiveness of an LLM Agent Loop with Tool Use. Parent comment

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by vidarh on Friday May 16, 2025 @06:52AM (#44003823)
They've written most of the recent iterations of X11 bindings for Ruby, including a complete, working example of a systray for me.

They also added the first pass of multi-monitor support for my WM while I was using it (restarted it repeatedly while Claude Code worked, in the same X session the terminal it was working in was running).

You do need to reign them back in, sure, but they can often go multiple iterations before they're ready to make changes to your files once you've approved safe tool uses etc.

[ Parent | on HN ]
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by datpuz on Friday May 16, 2025 @10:59AM (#44006316)
Agents? Doubt.
[ Parent | on HN ]
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by vidarh on Friday May 16, 2025 @11:03AM (#44006364)
You can doubt it all you want - it doesn't make it any less true.
[ Parent | on HN ]
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by datpuz on Friday May 16, 2025 @01:03PM (#44007669)
Can you provide a source
[ Parent | on HN ]
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by vidarh on Saturday May 17, 2025 @04:21PM (#44016724)
The statement was about what I have personally done, so I am the primary source.
[ Parent | on HN ]
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by TZubiri on Friday May 16, 2025 @06:13PM (#44010232)
How do they read the screen?
[ Parent | on HN ]
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by vidarh on Saturday May 17, 2025 @04:22PM (#44016730)
It didn't. For those tasks there were no need for it to. For the systray, I had to a couple of times provide debug feedback of the type "the window is visible now", and that was it.
[ Parent | on HN ]