Top all-time · #20712
Florian Herrengt
Personal blog · blog.florianherrengt.comaicareerprogramming
Florian Herrengt's personal blog at blog.florianherrengt.com covers ai, career and programming. Since 2025, 3 different Hacker News readers have linked it 12 times, most often “How LLMs Work”. It is still writing: the last post was on 2026-08-26, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
Linked as a prior post on AI displacing mid-level software engineers and the career prospects of vibe coders. The comment quotes the post's claim without judging the writing.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- How LLMs Work2 people · 8 mentions · first linked 2025-08-15
What Hacker News says?
- i have bearish from day 1 - i have no idea how anyone thinks the mighty next token predictor is going to eradicate diseases and eliminate poverty https://blog.florianherrengt.com/how-llms-work.html - i also have no idea what everyone and their momma on HN is running for more than 5 mins in the name of "agentic AI"
Comment linking /how-llms-work.html
on “Why I'm still bearish on LLMs after Navier-Stokes”Submitted The vibe coder's career path is doomed as a story · 122 points
HN discussion- its just a next token predictor with a high probability bro https://blog.florianherrengt.com/how-llms-work.html - when are all the "I am running agents 24x7 a day on max plan" people on HN gonna learn this? - best case scenario bro: LLMs get infinitely better and nobody needs to code anymore "software requirement prompting is the new skill" I can write those pretty well bro - worst case scenario: AI market crash,…
Comment linking /how-llms-work.html
on “AI Can Make You Suck Faster Too”Submitted How to automate Instagram engagements with computer vision (and get banned) as a story · 8 points
HN discussion- It is a next token predictor OP https://blog.florianherrengt.com/how-llms-work.html - deal with it and stop whitewashing, greywashing it
Comment linking /how-llms-work.html
on ““Next-token predictor” is the wrong mental model for LLMs”Submitted AI is removing the middle class of software engineering as a story · 4 points
HN discussion- i dont understand why anyone wants to sit and tell their entire personal life to it - it is just a next token predictor https://blog.florianherrengt.com/how-llms-work.html
Comment linking /how-llms-work.html
on “What We Tell AI”Submitted How LLMs Work as a story · 2 points
HN discussion- unrelated but from your blog - you have a very nice article on how llms work here https://blog.florianherrengt.com/how-llms-work.html - but in your diagram titled "Word vectors plotted in semantic space" dont you think you need to add arrows to show where those vectors are actually pointing? - because i dont get how you arrived at this Using vector arithmetic, you can calculate: woman + (uncle - man) = aunt withou…
Comment linking /how-llms-work.html
on “AI is removing the middle class of software engineering”I wrote about this before. I don't think the vibecoders will have a job for a long time. At best, it will be minimum wage. See "AI Won't Take Your Job, Someone Using AI Will" > There's no lucrative middle ground where 'AI whispering' is a high-value skill. https://blog.florianherrengt.com/vibe-coder-career-path.html
Comment linking /vibe-coder-career-path.html
on “AI is removing the middle class of software engineering”- https://blog.florianherrengt.com/how-llms-work.html hey there mojo jojo, might wanna read how llms work first
Comment linking /how-llms-work.html
on “The Problem”- https://blog.florianherrengt.com/how-llms-work.html isnt that how llms work? - did you change the architecture magically somehow?
Comment linking /how-llms-work.html
on “The Problem”