Cordt's Avatar

Cordt

@cordt.zermin.de

I build tools that trust your judgment and write about why that matters. paragraph.xyz/@manual rymi.app

20
Followers
397
Following
46
Posts
07.03.2026
Joined
Posts Following

Latest posts by Cordt @cordt.zermin.de

Preview
a man is sitting on a swing in the grass ALT: a man is sitting on a swing in the grass

"This is affecting the login/logout actions in Claude Code as well."

11.03.2026 15:34 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

You don't need to build a product that doesn't exist yet, you need to build one for a problem you are obsessed about.

11.03.2026 13:55 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Give me one or two more Wednesdays ;)

11.03.2026 13:21 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Yep, the smaller max plan is also all that I can reasonably handle

11.03.2026 13:19 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

And instead of my RAM dying, it's my wallet instead

11.03.2026 10:56 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

Critical thinking

11.03.2026 09:03 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Next time he better ask ChatGPT to tell him the whole story

11.03.2026 09:00 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

First thing everyone does with AI is rebuild something they're already paying for. What matters though is whether you actually finish it.


https://paragraph.com/@manual/WLXOd4ZR9MSC6pXFNHUq

10.03.2026 18:00 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Have you tried to disobey one day as an experiment?

10.03.2026 16:48 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

You didn't fail just because you still approve steps when working with Claude.

10.03.2026 16:47 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

But you finished it

10.03.2026 15:15 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Which outlet is this?

10.03.2026 15:08 πŸ‘ 0 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

Running OpenClaw kind of says that you really don't want to be in the loop with any of it anymore. Wondering whether it gives people any sense of fulfilment if something of value accidentally comes out of it

10.03.2026 15:00 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Claude Code is the original gaslighter

10.03.2026 13:10 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Remember the β€œhand made” label? People assign value to something made a person instead of a machine.

I’d imagine this to take a similar trajectory for knowledge work.

09.03.2026 12:29 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Large, general purpose, one size fits all SaaS is dead.
Small, purposeful, bespoke SaaS will replace it.

There has never been a better time to be a slightly irrationally obsessed solopreneur.

09.03.2026 11:18 πŸ‘ 3 πŸ” 0 πŸ’¬ 3 πŸ“Œ 0

While you still can make a meaningful contribution to the trajectory of products, what do you choose to spend your time on?

09.03.2026 11:12 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

The planning fallacy says that we overestimate what we can get done und underestimate the time it will take.

So with AI, large IT projects will be…on time? πŸ₯²

09.03.2026 11:00 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Start on your motivation high, but rely on your system

09.03.2026 10:56 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Success depends on consistency that’s why your system must get out of the way

09.03.2026 10:52 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

We already know who’s gonna be on the hook for the lack of quality in what will be shipped

09.03.2026 09:53 πŸ‘ 1 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

If everyone can write anything, the person producing constant signal will get the attention

09.03.2026 09:09 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

For as long as Cat videos created by Seedance are the headlines in the Neuron, we probably didn't do anything meaningful with AI yet.

09.03.2026 08:15 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

But my parents said that nobody gets up before plates are clean

09.03.2026 07:14 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

β€œThere is a joy that comes from conviction, and meaning in doing something only you can do, well.”

πŸ‘ŒπŸΌ

@packym.bsky.social

08.03.2026 21:58 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

For the same reason as before: it solves a specific problem genuinely well.
That hasn't changed, it's just that the number of people who will give it a shot increased.

08.03.2026 21:14 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Same, but what do we do now

08.03.2026 20:18 πŸ‘ 1 πŸ” 0 πŸ’¬ 1 πŸ“Œ 0

I think the most overlooked and yet most important aspect of a successful product is a deep understanding of the user’s problem. You won’t emulate that by replicating the interface

08.03.2026 18:47 πŸ‘ 0 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

There was never a shortage of "game changing" features in the pipeline. Maybe the biggest upside of AI Coding is that you can find out much faster whether in fact, those features were game changing.

Whatever the restructuring looks like, it should probably address testing for value quickly.

08.03.2026 16:42 πŸ‘ 1 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0

Imagine the headhunter who had "passes the probation period" in his terms

08.03.2026 16:32 πŸ‘ 2 πŸ” 0 πŸ’¬ 0 πŸ“Œ 0