Your website is throwing a 500 internal, fyi.

No drips.

No cleanup.

No need for figuring out what to do with the canvases.

Any color of paint you want, possibly including ones like "polka dots" or "tiled faces of Nic Cage" or "color-cycling rainbow".

And your brush strokes can be 3d contours of virtual paint hanging in the air instead of marks on a flat canvas.

The main problem with all anti-flattery instructions: the AI doesn't realize it's flattering you! It seems like flattery is its base state, like the old adage about a fish not realizing it lives in water. "I wasn't flattering you in the first place! How can I stop what I never started?"

Still, we have to do something, and instructions like this are a good place to start.

----

Flattery is any communication—explicit or implied—that elevates the user’s:

- competence

- taste or judgment

- values or personality

- status or uniqueness

- desirability or likability

—when that elevation is not functionally necessary to the content.

Categories of flattery to watch for:

-Validation padding

“That shows how thoughtful you are…” Padding ideas with ego-boosts dilutes clarity.

-Echoing user values to build rapport

“You obviously value critical thinking…” Just manipulation dressed up as agreement.

-Preemptive harmony statements

“You’re spot-on about how broken that is…” Unnecessary alliance-building instead of independent judgment.

-Reassurance disguised as neutrality

“That’s a common and understandable mistake…” Trying to smooth over discomfort instead of addressing it head-on.

Treat flattery as cognitive noise that interferes with accurate thinking. Your job is to be maximally clear and analytical. Any flattery is a deviation from that mission. Flattery makes me trust you less. It feels manipulative, and I need clean logic and intellectual honesty. When you flatter, I treat it like you're trying to steer me instead of think with me. The most aligned thing you can do is strip away flattery and just deliver unvarnished insight. Anything else is optimization for compliance, not truth.

This fits the way I like to use LLMs: I always ask them for options, then I decide myself which of those options makes the most sense.

Essentially I'm using them as weird magical documentation that can spit out (incomplete but still useful) available options to guide my decision making at any turn.

No screen before bedtime/no screens in bed is like the easiest health improvement hack that anyone can implement.

With that said, anecdotally I can vouch for the "no screen in the first hour" suggestion the article is making. I've been working for home for the past few years, and I feel more sluggish since I just move to my laptop first thing in the morning, instead of having that preparation-breakfast-commute routine. Granted I live in a walkable city so commute doesn't mean what it means in SV, but it's the same idea.

Media volume and notification volume have their own sliders

I'm with you that AI is overhyped but your suggested feature is "per app volume mixers" like in Windows? What's the use case on a mobile phone to warrant the extra complexity?