News for hackers. Stuff that matters.

tahigichigi

Re:The revolution in running agents 24/7 on Thursday May 28, 2026 @02:57PM (#48313753)
This is an online joke I created, please buy into more agent madness. thank you.
Re:/Deslop on Thursday February 19, 2026 @09:26AM (#47074081)
what's unbelievable about it?
Re:/Deslop on Thursday February 19, 2026 @09:25AM (#47074074)
but if I did you wouldn't be writing about it
Re:/Deslop on Thursday February 19, 2026 @09:25AM (#47074067)
not as catchy though is it
Re:/Deslop on Thursday February 19, 2026 @09:24AM (#47074059)
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

Re:/Deslop on Thursday February 19, 2026 @09:15AM (#47073963)
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)

Re:/Deslop on Thursday February 19, 2026 @09:13AM (#47073929)
Wow. We are not worthy.

What would you say are the top 2 red flags missing from the piece? Would love to know

Re:/Deslop on Thursday February 19, 2026 @09:12AM (#47073921)
there's a downloadable prompt at the bottom that'll kill any slop dead. Will replace with a Notion link to keep it updatable
Re:/Deslop on Thursday February 19, 2026 @09:10AM (#47073902)
This anon gets it
Re:/Deslop on Thursday February 19, 2026 @09:10AM (#47073895)
this sentence feels LLM written
Re:/Deslop on Thursday February 19, 2026 @09:09AM (#47073883)
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.

Re:/Deslop on Thursday February 19, 2026 @09:05AM (#47073850)
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.