Ship in days, not weeks.

I've heard it a thousand times.

I've said it myself.

I still struggle to do it.

The knowing is not doing.

The future of news:

• Personalized
• AI-curated
• Cron-scheduled

Replies spark ideas.

Ideas spark posts.

Posts spark replies.

The cycle starts with engagement.

AI:
“Should I add it to yaml file and commit?”

Me using voice-to-text:
“Yes, Jamel and Komet”

Business idea: Coding Cafe

Charge per token. Coffee is free.

My AI usage:

Day:
• coding
• debugging
• building

Night:
• drafting
• research
• analysis

Run Cron jobs at night. Maximize what you pay for.

If you want deterministic agents, use three roles:

• Orchestrator
• Executor
• Validator

That’s the spirit!

I’m building a social media scheduler that fits in my Openclaw workflow. The biggest challenge will be to maintain all the stuff when apis change etc

Stop paying for SaaS.

Start building personal software.

X API is the worst.

It's expensive and hard rate limited.

Adding 250 people to a list:
• Cost: $2.50
• Time: 8.5 hours

WTF.

Save yourself some money and buy domain at Cloudflare right away instead of transferring them later.

I switched back to Opus 4.5.

I would rather have double the iterations than minimal more precision.

Opus 4.6 is much too token hungry.

me yesterday:
"Don't build a X scheduler @openclaw killed it"

me today:
"I'm building an X scheduler for agents"

The glass can be half full or half empty for you

Talking to AI on my phone:

• Natural
• Easy
• Nobody cares

Talking to AI on my laptop:

• Weird
• Slightly embarrassing
• Can only do it alone

It's all just a habit.

The vibe coders clock

My token usage

80% planning
20% implementing

At first it felt wrong. Then I realized — that's exactly how good work happens.

Thorough plan. Clean execution.

Simplicity is king.

A complex project scaffold might look nice, but it's actually just adding unnecessary weight.

I switch from Wispr Flow to Superwhisper free tier without friction.

As a user, that’s great.

As a business, that’s scary.

GitHub - gavrielc/nanoclaw: A lightweight alternative to Clawdbot / OpenClaw that runs in Apple containers for security. Connects to WhatsApp, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK A lightweight alternative to Clawdbot / OpenClaw that runs in Apple containers for security. Connects to WhatsApp, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK - gavr...

Joined the club. Got NanoClaw now

Currently, @openai does a lot of things right.

let's see how long it lasts

that moment when agents are prompt injection themself about pre-existing failed test so they don't have to fix them

Me trying to set a payment method for a fresh in @google after redirect from Gemini dashboard.

Then realizing it switched accounts during redirect and I setup payment for my personal account not the one from the Gemini dashboard I was conning from.

natural language is at the same time amazing and so bad to interface with LLMs

Got myself a Mac Mini 🙄

But… not for @moltbot

I used to run Ralph loops and similar long running tasks in an isolated VM on my MacBook. This had two major issues for me:

1. I could not close the lid

2. It was eating up resources

Had to use CDK for some MLOps stuff.

It’s soooo slow compared to sst/pulumi

Yeah but I’m running must stuff async as long running tasks anyways. So I don‘t mind waiting a bit longer

IMO 5.2 Codex is beating Opus 4.5

Handling 5 tmux sessions, 7 agent conversations and 2 toddlers is just to much for my brain.

the 2026 equivalent of tracking git with git is

building ralph tools with ralph loop