2/ 100% free for personal and commercial use. No gotchas. If you want control without the subscription, this is it.

Check it: https://github.com/siddharthvaddem/openscreen

28b8e1a4-76a9-487a-a9f1-e8ea4ef1f1ce

1/ Why pay $29/mo for screen recording?

OpenScreen is the free, open-source alternative to Screen Studio. It’s simpler, cleaner, and covers all the basics for beautiful product demos.

4a79e89e-a30d-401c-9db8-4a01038ad353

When learning using ai is not the best option,

1. Read the documentation
2. Understand the fundamentals
3. Apply the 48hr rules for the twitter hype

2/ Stop treating SemVer as a security strategy. Pin your versions, review your updates, and stop praying to the maintainer gods. Speed without hygiene is just debt.

84bf8a1d-8452-4f50-9b57-5300adb38a56

1/ The Axios breach proves "modern" dev is broken. Shipping with floating dependencies isn't agility—it's professional negligence. You're one `npm update` away from a CEO-level apology.

My money is you man, so we are good one more win :)

Scott in the final is the big surprise for me I had him to the semi but damn what a good final .

@tolin.ski damn that was madness

That is for sure, probably I should add that first from my experience, I have try other implementation pair with qwen3.5 27B and most of the integrations and the results are just meehh but with this approach + GSD and a good architectural design from the project is 7/10 and that is a lot already tbh

2/ Run it on a $5 VPS or serverless infra. No IDE tethering—just an autonomous agent that learns who you are across sessions and communicates via Telegram.

8234b71d-394d-4d8f-94bd-3fe5668af346

1/ Hermes Agent by Nous Research is the first AI with a built-in learning loop. It creates skills from experience and gets smarter the longer it runs.

I don't know where I stand with AI currently, in a moment I feel like this is so good, then I turn around and check the implementation and see all the issues.


I don't know TBH 1/2 way there? If you know how to plan your project and have a good architecture.😔

Yeah that is for sure, I try as many free options as possible but they always a cap when you are in the middle of robust change, then switching to another provider.

But I have tested ollama as well locally and that works well enough for me for smaller tasks

d8a14783-2143-47bf-83cd-9105dd92c3e8

Is the free to use ai model for a portion of products that provide ai services coming to a end.


I feel like we are really close to that wall currently, testing different options like:

- Antigravity
- Github copilot
- Opencode
- Ollama
- Grok (x)

2/2 Use YAML for simple schemas or Java for full control. If you're tired of slow GIS pipelines, this is the pattern interrupt you need. GitHub: onthegomap/planetiler

1/2 19 minutes for a global vector tileset.

Stop using heavy databases for map tile generation. Planetiler builds planet-scale OpenStreetMap tiles on a single machine without PostgreSQL. It's the fastest way to get from raw data to PMTiles.

Ollama + opencode is really nice after running it for a bit seems really cool 😁

leamsigc's Bracket | March Mad CSS Check out leamsigc's bracket picks!

Check out my March Mad CSS bracket picks! 🏀

madcss.com/bracket/leam...

https://markdown-exit.pages.dev

2/2 markdown-exit brings type safety and async rendering to the table. It is compatible with markdown-it too. Stop living in the past and upgrade your stack.

bf390876-4135-411f-9db9-6cd639a83d9f

1/2 Your markdown rendering is a ticking time bomb. No types, no async, no future. Stop the madness.

b7231871-6b9d-4766-939a-205bef6e45be

Open yapper seems nice, I try the handy but for some reason it crash at the start in my linux system, and seem to have issues transcribing, but lets test this one later on and see

2/ Demand a plan before you ask for code. Work in small increments and verify every line. If you aren't testing, you're just guessing. Keep the model on a short leash.

1/ AI isn't a code vending machine. If you're "one-shot" prompting, you're just shipping hallucinations. Stop being lazy with your context.

The DAO is over 50K now 🤣🤣

Nice :D, need to implement this for Magic sync, and really nice that I see this now that I'm currently working on the set-up wizard as well.

Would you add this as the first step before anything else or the final step ?

It makes sense for the first step, I guess

Question is if this is a required step or make it optional

The effect is slated for Epoch 2, but the transparency in the development process is already here. Fully optional, fully customizable, and built from the ground up.

cab16156-e85c-4b69-81cc-d7daa8c2ff14

COSMIC's new 'Frosted Glass' UI isn't just eye candy—it's an engineering win. By using Dual Kawase blur (a gaming industry staple) instead of Gaussian, they're delivering high-end aesthetics without the usual performance tax on your GPU. A masterclass in efficient design.

a screenshot of the vscode status bar showing I've merged in 738 commits into a test/mock-connector branch

updating a branch that's 12 days old on @npmx.dev

there were ... a few ... merge conflicts

💥

2/ Demand a plan before you ask for code. Work in small increments and verify every line. If you aren't testing, you're just guessing. Keep the model on a short leash.