Hacker News: fenix1851

New comment by fenix1851 in "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)"

fenix1851 — Fri, 22 May 2026 05:50:05 +0000

it’s a different story.

I was highly interested in reading this article from start to finish.

Ofc there are was a lot of slop moments, but author experience itself is great!

And i genuinely don’t care if he would share it through LLM article.

Just please remove slop markers :)

New comment by fenix1851 in "Ten Signs of Fascism. America has all of them"

fenix1851 — Sun, 17 May 2026 08:30:35 +0000

Wonder how many times i saw this article with different countries…

New comment by fenix1851 in "Show HN: Bored, so I graphed 2M Telegram users by their gifts"

fenix1851 — Thu, 26 Feb 2026 14:21:01 +0000

Crazy! Is there any statistics about percent of users who’s using gifts?

New comment by fenix1851 in "Ask HN: How do you know if AI agents will choose your tool?"

fenix1851 — Tue, 24 Feb 2026 06:07:38 +0000

I think this thing you mentioned is more about reverse-engineering web-search tool call to understand how model formulate their response.

The tool i’ve didn’t see - “custdevs for agents”. So we can simulate choosing process for them in thousands of different scenarios. And then compare how tasty product looks for Claude or Gemini or any other LLM

Correct me if i’m wrong :)

New comment by fenix1851 in "Ask HN: How do you know if AI agents will choose your tool?"

fenix1851 — Tue, 24 Feb 2026 05:42:23 +0000

Is there are some additional tool/service/instrument that can measure it?

I mean how do i check that my changes in documentation even work in a right way?