ahrzb
Re:Hybrid Reasoning Agents: LLM agents that think in latent space, act...
on Monday October 19, 2026 @06:54AM (#50150811)
I find this the most natural idea, there is no reason to assume thinking in words is the right granularity, or will stay the right granularity.
Re:ZCode – Harness for GLM-5.2
on Wednesday July 01, 2026 @05:25PM (#48753337)
At least the model weights are open, I’m not American, so to me this is much more trustworthy in every possible way.
You’re talking as if US intelligence are the good guys, and to me at least, they are not to any extent.
Re:Ask HN: Do tech certifications matter nowadays for hiring?
on Sunday October 22, 2023 @07:05PM (#37979878)
At the current pace, courses get out of date a bit too fast. I don’t see any reason to take them seriously as long as this dynamic holds. Do a course if you think it has some valuable content or maybe do some and get certificates to get your first job, but that’s the extent of it.
Re:Git Blame-Someone-Else
on Sunday June 04, 2023 @07:00AM (#36184632)
But changing commit author is quite easy with git, just do: ‘git commit -a —author “<name+email>”’
Re:Git archive generation meets Hyrum's law
on Friday February 03, 2023 @03:17PM (#34647130)
That’s mainly for security reasons, mainly preventing Hash DDoS attacks, therefore a requirement.
Re:Faster CPython 3.12 Plan
on Tuesday September 20, 2022 @10:32AM (#32912154)
I don’t think so, there are some design choices that make the two quite different. This „dictionaries all the way down“ approach has a cost.