Re:Running Gemma 4 26B at 5 tokens/SEC on a 13-year-old Xeon...
by twoodfin on Wednesday July 15, 2026 @04:06PM
(#48926392)
The post is absolutely LLM-generated. “Punchy” short sentences, “… has quietly come to mean …”, “The optimized paths weren’t there to execute.”
Re:Running Gemma 4 26B at 5 tokens/SEC on a 13-year-old Xeon...
by logicallee on Wednesday July 15, 2026 @01:47PM
(#48924554)
I think "this" refers to its parent comment. Part of it sounds like Claude wrote it. AI-generated comments aren't allowed on HN.
Re:Running Gemma 4 26B at 5 tokens/SEC on a 13-year-old Xeon...
by otherjason on Wednesday July 15, 2026 @03:16PM
(#48925755)
Indeed, I was referring to the parent comment.
Re:Running Gemma 4 26B at 5 tokens/SEC on a 13-year-old Xeon...
by why_only_15 on Wednesday July 15, 2026 @10:15PM
(#48929651)
The post itself is totally AI-generated. It has tons of tells, in addition to Pangram saying so.
https://www.pangram.com/history/61fbc90e-180d-4d91-a85d-16ff...
I don't think the post itself reads like AI at all, but that's just me.