“An intelligence layer reads satellite imagery, predicts sediment flow, determines placement, and improves with every new site; demand is rising from resorts, private owners, nations facing sea-level rise.”
18GB was an odd 3-channel one-off for the M3 Pros. I guess there's a bunch of them out there, but how slow would 27B be on it, due to not being an MOE model.
Qwen3 coder next works very well. I started with 20usd/month ollama cloud and switch to 200usd then decided host my own llm with a gigabyte ai atop since now i'm using llms agents everywhere on my home lab
People deserve to know it exists, I got tired of even OpenCode workflows/agents, installed OpenSpec but all this wrapped todos still not how i wanted
I needed more control but dint wanted to write my own tool, then i ended knowing about pi, this got me interested at first read:
No plan mode. Write plans to files, or build it with extensions, or install a package.
No built-in to-dos. Use a TODO.md file, or build your own with extensions.
No background bash. Use tmux. Full observability, direct interaction.
This is very important to have control and ownership.
Pi is not for everyone, but the ones eventually want to have tools like (read, bash, edit, write, grep, find, ls) as building blocks.
reply