pull down to refresh

105 sats \ 2 replies \ @rolznz OP 2 Jun \ parent \ on: A Sovereign Brain on a Laptop: Local LLM + Pi Agent + Markdown AI

Interesting that we got basically the opposite results :-)

I do see a LOT of errors, yeah. But from my observations it's very good at self-correcting and fixing its mistakes.

But this project is quite simple - not much specific technical knowledge needed. Maybe this is where the difference comes from?

I also saw you used Claude Code and OpenCode. They both use a large system prompt. Did you try Pi Agent?

write
compose
15 sats \ 0 replies \ @optimism 22 Jun

Reporting back in.

Did you try Pi Agent?

I wanted to run some tests with GLM-5.2 and opencode stalled out on me twice, so I quickly implemented pi agent and hung it into my framework (w/ ppq) and this seems to work better than opencode. It finished the assigned job without issues and with minimal token burn. I'll re-test Qwen 3.6 with this later in the week / weekend.

reply
456 sats \ 0 replies \ @optimism 2 Jun
I do see a LOT of errors, yeah. But from my observations it's very good at self-correcting and fixing its mistakes.

This I see too (it's better trained at this than Gemma) and I do think the self-correction is working more often than not (though what a waste of compute!) grep -i wait on thinking blocks is still "fun" too.

But this project is quite simple - not much specific technical knowledge needed.

My main use case nowadays is feeding LLMs file diffs and strace logs, mostly of third party code from npm/cargo/pubdev/mvn/pypi, to help me make security assessments. Thanks to LLMs this now only takes me a day a week instead of 4 last year, with about 5x the workload and an 100x threat increase.

Did you try Pi Agent?

Nope. The problem I'm running into is that I am swamped, but I'll try to find a moment to test your setup.

reply