News for hackers. Stuff that matters.
Re: by kstrauser on Monday June 08, 2026 @12:11AM (#48441253)
We’re using vastly different models, then, because it doesn’t read like any generated text I’ve seen before.
Re: by ike_a on Monday June 08, 2026 @12:38AM (#48441388)
What models are you using? This looks incredibly similar to the outputs I get from Claude with default system prompt settings.

- First, take a look at the other articles. There are 30+ articles all with the same author published this week on topics from cooking to home appliances. Either he's extremely prolific or had help.

- There's so much click-baity LLM language: "The radial gradient: why edges undercook on every hob" "What “crispy” actually means: acoustic fracture mechanics" "What Actually Matters"

It's clear to me that at least some of this is LLM generated, so all of it might as well be.

Re: by zahlman on Monday June 08, 2026 @12:34PM (#48447552)
> There's so much click-baity LLM language

You're absolutely right. It's not just Claude that gives you output like this — it's every model.

(Ahem, sorry.)

Re: by shalmanese on Monday June 08, 2026 @01:24AM (#48441606)
"The three effects are not separable knobs. You cannot dial in one without moving the other two.

The browning claim is the contested one, so it is worth pinning down. "

Is classic Claude-speak.