News for hackers. Stuff that matters.

A comment on Run a 1T parameter model on a 32gb Mac by streaming tensors from NVMe. Parent comment

Re:Run a 1T parameter model on a 32gb Mac by streaming tenso... by password4321 on Tuesday March 24, 2026 @12:50PM (#47505606)
Don't post generated/AI-edited comments. HN is for conversation between humans

https://news.ycombinator.com/item?id=47340079

[ Parent | on HN ]
Re:Run a 1T parameter model on a 32gb Mac by streaming tenso... by tatef on Tuesday March 24, 2026 @02:36PM (#47507177)
Noted, thanks. I had LLM help positioning this message but I did the initial draft along with edits. Will keep in mind for the future.
[ Parent | on HN ]
Re:Run a 1T parameter model on a 32gb Mac by streaming tenso... by DennisP on Tuesday March 24, 2026 @01:15PM (#47505993)
That doesn't read like an AI-generated comment to me. He did mention he vibe-coded the project but that's not against the guidelines.
[ Parent | on HN ]
Re:Run a 1T parameter model on a 32gb Mac by streaming tenso... by Retr0id on Tuesday March 24, 2026 @01:26PM (#47506192)
It's either written by an LLM, or written by someone who learned to write by reading LLM output
[ Parent | on HN ]
Re:Run a 1T parameter model on a 32gb Mac by streaming tenso... by password4321 on Tuesday March 24, 2026 @01:27PM (#47506202)
Vibe-coded project is fine.

At least prompt your LLM to dodge the obvious tells when commenting!

[ Parent | on HN ]
Re:Run a 1T parameter model on a 32gb Mac by streaming tenso... by Forgeties79 on Tuesday March 24, 2026 @01:23PM (#47506143)
gptzero says 99% chance it’s AI-generated

It certainly has a lot of telltale signs

[ Parent | on HN ]
Re:Run a 1T parameter model on a 32gb Mac by streaming tenso... by Izikiel43 on Tuesday March 24, 2026 @01:17PM (#47506049)
> The core insight:

That's a telltale sign of ai written text.

[ Parent | on HN ]