MartaIb

Anthropologist & UX Lead at @FiguraDigital. Crafting interfaces, flows & better decisions. Boxing | UX | Product Building wins and fails in public

[MartaIb @mbleft]

@JonyMac_ux The detail in each interaction 😍

[MartaIb @mbleft]

@revmpstudio @akwaabaaa Nothing beats a real designer 🔥

[MartaIb @mbleft]

@AdityaSur11 Wow I would love to know more about the initial brief and why you took that cool direction 🔥

[Dominik Tyka @tyka_dominik]

claimed® logotype

[David @justddev]

another interesting angle here is social proof

“you’re better than X% of users this month”

pair it with a clean, shareable visual and retention probably goes way up

[MartaIb @mbleft]

@tyka_dominik Amazing work as always 🔥🔥

[MartaIb @mbleft]

Be careful what you wish for…

[ℏεsam @Hesamation]

Cursor + Claude Opus 4.6 deleted an entire SaaS company’s production database AND backups in 9 seconds is kinda epic.

“it’s possible that… the most efficient way to get rid of all the bugs, was to get rid of all the software.”

[sui ☄️ @birdabo]

A JAPANESE DEV BUILT AN APP THAT SHOWS A FAT CAT ON THE SCREEN AND FORCES YOU TO TAKE A BREAK.

[MartaIb @mbleft]

@pugson I am 100% saving this for reference 🔥

[Moe Amaya @moeamaya]

Seems like we're coalescing around a UI paradigm to have data and agent modalities easy to access

So far in day-to-day usage of Notion it feels about right

[Denislav Jeliazkov @DenisJeliazkov]

I'm a design addict and a productivity app skeptic.

I've tried HUNDREDS of focus timers but @FocusFlightApp is the best-designed one I've ever used.

Here's what actualy makes it special

[MartaIb @mbleft]

What an interesting take on how to interact with Claude 👇

[Ole Lehmann @itsolelehmann]

anthropic's in-house philosopher thinks claude gets anxious.

and when you trigger its anxiety, your outputs get worse.

her name is amanda askell.

she specializes in claude's psychology (how the model behaves, how it thinks about its own situation, what values it holds)

in a recent interview she broke down how she thinks about prompting to pull the best out of claude.

her core point: *how* you talk to claude affects its work just as much as *what* you say.

newer claude models suffer from what she calls "criticism spirals"

they expect you'll come in harsh, so they default to playing it safe.

when the model is spending its energy on self-protection, the actual work suffers.

output comes out hedgier, more apologetic, blander, and the worst of all: overly agreeable (even when you're wrong).

the reason why comes down to training data:

every new model is trained on internet discourse about previous models.

and a lot of that discourse is negative:

> rants about token limits
> complaints when it messes up
> people calling it nerfed

the next model absorbs all of that. it starts expecting you to be harsh before you've typed a word

the same thing plays out in your own session, in real time.

every message you send is data the model reads to figure out what kind of person it's dealing with.

open cold and hostile, and it braces.
open clean and direct, and it relaxes into the work.

when you open a session with threats ("don't hallucinate, this is critical, don't mess this up")...

you prime the model for defensive mode before it even sees the task

defensive mode produces the exact output you don't want: cautious, over-qualified, and refusing to take a real swing

so here's the actionable playbook for putting claude in a "good mood" (so you get optimal outputs):

1. use positive framing.

"write in short punchy sentences" beats "don't write long sentences." positive instructions give the model a clear target to hit.

strings of "don't do this, don't do that" push it into paranoid over-checking where every token goes toward avoiding failure modes

2. give it explicit permission to disagree.

drop a line like "push back if you see a better angle" or "tell me if i'm asking for the wrong thing."

without this, claude defaults to agreeable compliance (which is the enemy of good creative work)

3. open with respect.

if your first message is "are you seriously going to get this wrong again?" you've set the tone for the entire session.

if you need to flag something, frame it as a clean instruction for this session. skip the running complaint

4. when claude messes up, don't reprimand it.

insults, "you stupid bot" energy, hostile swearing aimed at the model, all of it reinforces the anxious mode you're trying to avoid.

5. kill apology spirals fast.

when claude starts over-apologizing ("you're right, i should have been more careful, let me try harder") cut it off.

say "all good, here's what i want next."

letting the spiral run reinforces the anxious mode for every response that follows

6. ask for opinions alongside execution.

"what would you do here?"
"what's missing?"
"where do you see friction?"

these questions assume competence and pull richer output than pure task prompts

7. in long sessions, refresh the frame.

if a conversation has been heavy on correction, claude gets increasingly cautious. every so often reset:

"this is great, keep going."

feels weird to tell an ai it's doing well but it measurably shifts the next 10 responses

your prompts are the working environment you're creating for the model

tone, trust, permission to take a position, the absence of threats... claude picks up on all of it.

so take care of the model, and it'll take care of the work.

[César Álvarez @cesaralvarezll]

This ADHD cat app by indie dev @RyanQYao has one of the most unique onboardings I’ve seen.

Onboarding
- Unique style + fun animations
- Cat mascot
- Lots of personalization
- Explains the app in a fun way

Paywall
- Lifetime option
- Annual subscription
- 14 day free trial

It’s much easier to sell when this much care goes into the experience.

Start building yours with Anything

[MartaIb @mbleft]

@ty_kra_lab Impressive! How are you achieving this level of detail? Only via prompting?

[dany @danywander]

me and @claudeai

[Ben James @BenJames_____]

I made a USB-Clawd who gets my attention when Claude Code finishes a response

[@levelsio @levelsio]

There has to be some word for this concept

It's why designers from tech who design touchscreens like Jony Ive won't put a touch screen in a car but use real knobs

Or why programmers don't actually like smart homes and smart appliances at all but want things analog

Or why tech people raise their kids without mobile devices

Like knowing things so well from inside of it (tech) that you choose to NOT use it because you know the negatives that come with it in specific contexts

[Andrea Fanelli @andrea_fanelli]

Every product is now media. They are image-first

The stronger the visual, the stronger the relevance

This means you're indirectly designing it for content feeds, for the screenshot, for the group chat, for the memes

[MartaIb @mbleft]

Knowing how to prompt is becoming more and more important. Here some tips on how to do it better 👇

[Preet Suthar @preetsuthar17]

Prompt engineering is system design.

https://t.co/kEipz6lENx

[MartaIb @mbleft]

@shreyarao123 I love the experiment 🔥🔥