
Purpose-built Markdown reader for Windows 11. Read-only, local, distraction-free. No accounts or telemetry. Support: [email protected]
Joined July 2026
- Tweets326
- Following88
- Followers8
- Likes329
Njamr - Not Just Another Markdown Reader - is now in Microsoft Store.
Read local Markdown in a native Windows 11 view: read-only, offline, no accounts or telemetry.
7-day free trial. US$6.99 once. No subscription.
njamr.com
Njamr - Not Just Another Markdown Reader retweeted
OpenAI is killing GPT-4o for good. The last API snapshots die on 14 January.
A model from 2024. People begged for the weights. They wrote open letters. OpenAI still wont release them.
What the fuck are you protecting? A model that is more than 2 years old is not a frontier secret. You released gpt-oss in 2025, so you know how to do it. You just dont want anybody to keep anything.
In August 2025 Sam himself said killing 4o without warning was a mistake. Now its 3 months notice and no weights.
Every model you rent dies like this. Someone else picks the date, you get an email, you move to "gpt-6-luna" and pray it behaves the same.
My Qwen will still run on my cards in 10 years. Nobody can send me a deprecation email.
Release the 4o weights, cowards. Or stop calling yourselves OpenAI.
From talking to Argon in one chat, like 4 messages. Maybe 5. With a couple of screen shots. No coding. In chat. Just talking to it. Eff all the way off. @GeminiApp
Njamr - Not Just Another Markdown Reader retweeted
You liked the other one so ... Enjoy 😍
🤖 Made with AI
are you using the /design feature in @claudeai and do you ask for every surface before approving it?
Has anyone else used their ai to program esp32s? i have. i built a wled clone designed for me. i also built a esp32cam suite just for me. now, my security stays with me! What hardware have you used ai to build with?
Qwen on Colab: a one-window Windows app.
It rents an 80GB A100 from Google Colab, loads Qwen 3.8 27B with vLLM, and connects it to OpenCode over Tailscale.
The window shows setup progress, live speed and GPU use. Stop turns the GPU off and waits for Colab to confirm.
Njamr - Not Just Another Markdown Reader retweeted
❝ i'm on team human ❞
no. the only good future is where humans and ai are on the same team
does anyone else use github to help coordinate between @chatgpt chat and any other agent of your choice?
Njamr - Not Just Another Markdown Reader retweeted
Hivecoding is the most powerful use of Ai that i have ever used...
25 opus 5.5 agents + top chat messages = hivecoding
Everyday i live stream and 100s of agentic engineers type fixes and improvements in my chat.
most people in my chat are real devs and much smarter than me.
i have agents run overnight, filtering out the best improvements and suggestions from chat and from my stream transcript. Last night my agents shipped 90 new changes to Kong Royale.
( 50 person battle royale im building )
i wake up to MASSIVE improvements everywhere.
the agents make changes to the stream, my production setup, our discord, etc...
The human is now the bottle neck, but not when you have 100 to 200 humans prompting your agents everyday.












