Hacker News Reader

They have a subsequent post (from Monday) about what they've been working on: https://rosmine.ai/2026/05/18/fixing-llm-writing-with-distri...

(I would assume they haven't made a lot of $ off of this, if nothing else because they've only just put out that post and demo. They do seem to have produced a model that doesn't sound very LLM-y to my ear, though it also seems rather weak for its size.)

View on HN

Shallow take: They made an LLM that uses fewer emdashes.

Cynical take: They made an LLM that can bypass existing AI slop detectors.

Realistic take: They found a research problem they found interesting, dumped a bunch of capital and sweat equity into and (claimed to have, at least) found a solution. Neat!

Or they just have lots of money and a hobby. Someone else might blow $48K to get an old Cessna and go have fun flying around. Not everything needs to have a purpose.

A self-described "broke grad student [who has] been saving up for this for years."

Risking their own money and time instead of leveraging a PowerPoint to hire other peoples' labor with other peoples' money. I can respect that.

You read that line wrong.

You were on the money with the Cynical take lol:

https://rosmine.ai/2026/05/18/fixing-llm-writing-with-distri...

Huh? That's them intentionally demonstrating the slop style.

Reply on news.ycombinator.com