

What’s wrong with ollama?


What’s wrong with ollama?


all good. same


acquisition?


Or LLM cleanroom copy it, like the internet did when claude code source was leaked into other languages like rust


That’s a good point. We’ve been using the UML diagrams as a tool to catch behavioral red flags, but the reuse and implementation details of that are left undefined.
Maybe the answer lies in also explicitly spending a few passes focusing on code health, explainability, maintainability (while keeping brain on). This is something I go through at end and then retry verification tests, but not something we explicitly require in our process at the moment.
But in the end you have to know what good looks like and be able to call bullshit. Hmm I guess strong first principles are still the foundation of being good at something, no matter how the tools change. And practice, feedback, and constraint exposure are what turn that into actual effectiveness.


We require you to submit markdown plan before working on a feature, which must have full context, scope, implementation details. Also verification tests mardown file of happy path and critical failure modes that would affect customer, and how tests were performed. Must be checked in with the commit. More complex, large features require UML diagrams of architecture, sequences, etc. to be checked in too.
If your plan or verification docs have wrong context, missing obvious implementation flaws, bad coupling, architecture, interfaces, boundary conditions, missing test cases, etc then PR rejected.
Every developer’s performance is judged as a systems engineer. Thoughtless features without systems docs and continued lack of improvement in your systems thinking gets you PIPed.


Battery life is limited by cell modem drivers being closed source and having to be reverse engineered.
I have been looking into an alternate hybrid radio device using Reticulum. Though with that comes a new less convenient user experience for a lot of apps.


Socialized losses are the norm. People’s energy bills are already paying for the nearby data centers .


I’m emphasizing breaking free from identity ties to devices enforced by the hardware/radio. Not adding it to all devices.
It also limits open source competition in the phone market.


And the hardware. Your phone requires much harder power optimization in order to have a usable battery life. Same for size and heat dissipation.
Also politics related to the radio connection. Public cellular is tied to identity. It is structurally hostile to user-controlled, fully open, deeply optimized devices because the radio stack is certification-heavy, operator-governed, and privacy-hostile.


People put doom on microwaves, I’d call that general purpose computing.
After reading that… it only pertains to commercially licensed?


To drive up fake usage numbers for justifying the bubble they created to shareholders.


I’ve heard ZorinOS is good if you want easy switch over from windows / want to keep similar UI


Given that this person’s boss wants them to dump company data into Claude, I see no functional difference.


The trick is to tell them you’ve been using it more than they have and that it’s not as good as chatGPT for task A, but that for task B claude does okay 25% of the time so we’ll need to 4x the timeline in order to get a good claude output based on that expected value.
But not as good as your personal local LLM that you’ve been training on company data. No one else can use it because it’s illegal to clone. (your personal local LLM is your brain)
Zorin OS is a good one if you want a nice UI transition from Windows or Mac.