May 29 I wrote my first AI trainwreck story. June 18 I finished #15.
People keep asking if this was some kind of "writing experiment" โ it wasn't....
For further actions, you may consider blocking this person and/or reporting abuse
After reading all these AI stories, my conclusion is simple: automation can replace tasks, but not context, intuition, and accountability. Thanks for sharing both the successes and the limitations of AI in such an engaging way.
"automation can replace tasks, but not context, intuition, and accountability" โ that's the whole series in one sentence. Glad you stuck around through all 15 ๐
@xulingfeng Thanks, cool to read that, much appreciated!
See you in the next series ๐๐
Sure thing - also good that you explained your main underlying motive for publishing this series - I completely understand and agree, I have the same feeling about some companies' knee-jerk reaction to AI, in that they think it's a good idea to get rid of their employees without much thought "because AI can do all that" (without proper human guidance or oversight) - I think they'll learn their lesson the hard way ...
David vs. Goliath, the score: 15-0 !
That 15-0 scoreboard is yours too. You were there from game 1. ๐
Hi leob, great to meet you here, do you mind being my tech mentor ?
technical PM writeups I was proud of sat at 2 reactions while a messy 'here's what went sideways' post broke out. story-first isn't just engagement bait - it's the honest format for anything worth learning from.
Exactly this. The messy ones are the only ones worth writing. Appreciate you being here through it all ๐
yeah, and harder to write too. making sense of the mess is the actual work
That's the part nobody tells you โ writing the clean version is easy because you just leave things out. Writing the messy one means you actually have to understand it first.
right, and the things you leave out are the parts that bite you later.
You just described the arc of every AI failure story I've written. The thing that broke was never the thing people were watching โ it was the context they trimmed because it seemed irrelevant at the time. Writing and deploying have that in common: what you leave out is usually what kills you.
Which detail bit you hardest that you almost left out?
Interesting!
Consistently consistent. Appreciate you, Benjamin ๐
that is so true! :)
๐คฃ๐คฃ๐คฃ
Lol :)
15 stories.
445 reactions.
251 comments.
The engagement economy is brutal. ๐
Wait, I wrote 15 stories and only got 445 reactions? That's 29.6 reactions per story. I'm clearly not optimizing my engagement-to-effort ratio correctly ๐
Congrats on wrapping up the series ๐
15 stories is no small thing. I can imagine how much work went into writing, revising, and keeping everything consistent.
I'll definitely be checking out whatever comes next.
Thanks Hemapriya! ๐ The 36 stratagems series starts next โ see you there ๐
Honestly, I have not noticed the links yet; the footer of the story is the part I always skip ๐
So I'm happy to buy you the first one; thanks for writing those stories, they made me smile a lot of times.
Haha you literally just made my week. First coffee from a reader who actually went through the whole series โ means more than you know. I'm not gonna lie, I almost teared up reading this ๐ญ Glad the stories landed ๐
This is a useful lesson for technical writing too. The story format works because it gives the reader a concrete failure, a person in the room, and a consequence. A pure AI tutorial often skips that and jumps straight to the tool. The tool is easier to explain, but the failure mode is what people remember.
That last line โ "the failure mode is what people remember" โ I think that's the whole point of writing in this format. Tutorials age, stories don't.
Reading this made me realize you're one of the reasons I kept writing on dev.to.
When I published my first post a few weeks ago, you were the first person to react, comment, and follow. At the time I had no idea whether anyone would care about what I was writing, and that interaction made it feel like I wasn't just shouting into the void.
I'm only three posts in, but your retrospective made me appreciate how much those early interactions matter. Thanks for being one of the people who showed up at the beginning.
This made my day. I remember that first post of yours โ glad I clicked on it. Three posts in and already making an impact. Keep going, man. ๐
Really glad the #6 vs #10 analysis landed. I almost cut that section because I thought it might come off as over-explaining, but it felt dishonest to just post the numbers without acknowledging that some of them stung. You're also right about the "buy me a coffee" thing โ 251 comments later, I'd take an inbox full of real stories over a tip jar any day. That's the part no one warns you about when you start writing: you go in thinking you want reach, but what actually keeps you going is knowing someone out there read your words and felt seen.
Speaking of what's next โ I've actually kicked off a new series already. First post is up rightย here. Would love to hear what you think โ your kind of feedback is literally the fuel that keeps me writing. Appreciate you ๐ค
the "failure modes are not fiction" line is the one that hits differently for AI engineers. we spend months writing "how to build an RAG pipeline" docs and almost nothing on "here's the third time our retrieval layer silently returned stale embeddings and the model confidently answered from six month old data."
the story format forces you to admit the retrieval was wrong, which is the only part anyone actually learns from.
curious whether you found the pacing changed between early stories (when readers didn't trust you yet) and later ones โ or did the same structure work throughout?
Great question. Early ones were tougher โ felt like every paragraph had to earn the reader's trust. Later ones came easier because people already knew the format and trusted it wasn't just a rant. Structure stayed the same: failure โ confrontation โ aftermath. What changed was how much setup I needed upfront.
Also โ "we write RAG docs, not stale-embedding postmortems" โ painfully true. Might borrow that ๐