HNHacker News
TopNewBestAskShowJobs

abhikul0

120 karma · joined February 23, 2026

She just gets bored sitting by the lake,

Her soul won't surface and her heart won't ache.

submissionscomments
abhikul0··on The Engine Behind the Hype
Pi works great for local models in my short testing. Wanted to try out Skills and how small models work with these agentic tools for small tasks, mainly [browser-use](https://github.com/browser-use/browser-use).

Tried Mistral Vibe, Codex, Opencode, Claude with gpt-oss:20b, ministral 3b,8b, Nemotron3 nano 30b and GLM 4.6V; finally settling on gpt for its impressive pass rates. All the other tools inject upto around 7-10k tokens on the initial prompt while pi takes up ~1.5k. This works out to be quite usable for my m3 pro machine that can take a while when processing the huge initial prompts from other CLIs.

While I'm not doing any serious work, and the other tools could be tweaked to use a simpler System Prompt; pi felt quick and the llms did use the tool calls correctly without being confused with all the huge prompts being dumped on them.

abhikul0··on Show HN: Local-First Linux MicroVMs for macOS
Thread from yesterday https://news.ycombinator.com/item?id=47101200
← PreviousPage 3 of 3