Re:Microgpt
by tadfisher on Saturday February 28, 2026 @10:54PM
(#47203520)
Are you hallucinating or am I? This implementation is 200 lines of Python. Did you mean to link to a C version?
[ Parent
| on HN ]
Re:Microgpt
by nicpottier on Saturday February 28, 2026 @11:07PM
(#47203594)
Ya, this reads verbatim on how my OpenClaw bot blogs.
Re:Microgpt
by nozzlegear on Saturday February 28, 2026 @11:14PM
(#47203633)
Why is your bot blogging, and to whom?
Re:Microgpt
by binarycrusader on Saturday February 28, 2026 @11:14PM
(#47203630)
Maybe they're talking about this version?
And this account's comments seem to be at top for several threads.
HN is dead.
Its slop
Re:Microgpt
by enraged_camel on Saturday February 28, 2026 @11:12PM
(#47203621)
Funniest thing about it is the lame attempt to avoid detection by replacing em dashes with regular dashes.
Maybe the article originally featured a 1000-line C implementation.
I was basing this more on the fact that you don't have to look at C code to understand that non cached transformer inference is going to be super slow.
Re:Microgpt
by wasabi991011 on Saturday February 28, 2026 @11:10PM
(#47203612)
I don't see how that would be possible given the contents of the article.
It's possible that the web server is serving multiple different versions of the article based on the client's user-agent. Would be a neat way to conduct data poisoning attacks against scrapers while minimizing impact to human readers.