tahigichigi
tahigichigi on Hacker News
Posted by
tahigichigi on Saturday August 15, 2026 @10:40AM
from the mooch.agency dept.
Posted by
tahigichigi on Tuesday June 23, 2026 @06:42PM
from the paulgraham.mooch.agency dept.
This is an online joke I created, please buy into more agent madness. thank you.
what's unbelievable about it?
but if I did you wouldn't be writing about it
not as catchy though is it
The best is when you use a speech to text app like Whispr Flow and just ramble to the AI about an idea or an experience, get your thoughts out and it returns a silhouette of an insight or article.
So when people say they never get a good output it's because they're trying to from
thought > article
instead of
thought > exploration > direction > structure > outline > article
tone of voice match is similar but different. That's why I made toneofvoice.app
AI can copy 90% of your tone of voice but still use em dashes and corrective antithesis.
Ideally you'll have both /deslop and /soundlikeme (coming soon)
Wow. We are not worthy.
What would you say are the top 2 red flags missing from the piece? Would love to know
there's a downloadable prompt at the bottom that'll kill any slop dead. Will replace with a Notion link to keep it updatable
this sentence feels LLM written
I guarantee if you give me your prompt and the output you got I can fix it and get you a 10x better output in less than 5 minutes.
DM me on substack if you don't wanna post it here, I'm honestly happy to help wherever I can.
OP here. You're absolutely right!
Most people drop a one line prompt like "write amazing article on climate change. make no mistakes" and wonder why it's unreadable.
Just like writing manually, it's an iterative approach and you're not gonna get it right the first, second or third time. But over time you'll get how the model thinks.
The irony is that people talk about being lazy for using LLMs but they're too lazy to even write a detailed prompt.