Dagens Vibes — 24. august 2026

recommended reading. i did quite a bit of "hard" stuff in my programming life. but i had to pick my battles, because even tho i knew how to do things, they still took a sometimes prohibitively long time to do. with agents, i can do a lot more hard things, and merely steer based on my knowledge and experience.

Armin Ronacher ⇌@mitsuhiko

Some weekend thoughts on how LLMs change the way we start new projects.

https://x.com/badlogicgames/status/2091448131804168558

One of the most cracked engineers I know believes that local development is (mostly) dead. He walked me through why + his setup for using cloud agents in parallel... The big fucking problem: - You've got one codebase on your computer - Worktrees are supposed to let you run agents in parallel. On a real stack they don't (database contention, port conflicts, a dev server that only works in one tree) - So people flip back to one agent at a time and become the bottleneck themselves - Or they run multiple agents on the same machine: one writes a change, another writes over it, and they're fighting - Then you have to poke around, find everything each agent did, and test it independently - That's too much mental clutter - Locally you're operating like a CPU. You get an instruction, you build it, you queue a backlog The solution: - Stop sharing the computer. Give every agent its own - @seejayhess' setup is @AmpCode "orbs": a full computer in the cloud that clones the repo, starts the dev server, and runs one agent with nothing else contending - A "portal" is a live URL into that running app so you can click around from any device before you trust it - Isolated like an actual team, each person on their own machine The payoff: - It feels like a GPU, not a CPU. A list of 10 tasks, all started, real progress, loop closed - Smaller, contained diffs hit main faster and create fewer conflicts, not more - Favorite prompt: "give me irrefutable evidence that this works." On his laptop he would never run something so heavy he can't use Slack and Chrome. In an orb he will (millions of simulated DB writes, full demo videos) - Smaller diffs, no mixed concerns, higher confidence, ship more often - Mental clutter is gone. One thread, one set of changes, one computer. He always knows the state. That's what lets him do more in parallel, not less - The last things he still does locally: read production logs, set a sensitive secret. He is not spinning up the app on his laptop

https://x.com/businessbarista/status/2091596162625163643

This could help a lot of local model users if claims are true 👀

Shuo Yang@Andy_ShuoYang

FreeToken is fast. Comparing to Ollama, we have 3–4× faster decode, and 6–30× faster prefill How? We introduce bandwidth-adaptive CPU–GPU execution + semantic-aware caching across agent turns. More details in the technical report.

https://x.com/Teknium/status/2091704881681948941

I'm kind of iffy on "skills discourse" but I think I came up with one so good that its worth sharing. The basic ask is to "describe the UX of my application completely". In doing so, agents will discover inconsistencies, bugs, and design errors that have never come up before

https://x.com/steveruizok/status/2091595981603185077

Making progress on my Californication game with Claude Code Desktop, Threejs, and Higgsfield - No, I didn’t build it with one prompt - Yes, there’s a lot of iteration - I have shared objects across all scenarios, like the red tokens - And scenario-specific ones, like Bigfoot Building games with Claude Code is fun. You don’t need endless loops or one massive prompt to make something cool Just enjoy the process!

https://x.com/dani_avila7/status/2091627680177262824