Show HN: Symbio self fine-tuning AI loop

hhuyedit about 6 hours ago 3 commentsRead Article on github.com

RU version is available. Content is displayed in original English for accuracy.

It trains based off the mistakes it made with the solution you gave OR what it got. Thank you for reading

⚡ Community Insights

Discussion Sentiment

50% Positive

Analyzed from 112 words in the discussion.

Discussion (3 Comments)Read Original on HackerNews

ChulioZ•about 5 hours ago

I place a lot of importance in my own projects that every agent session captures non-obvious learnings as rules and that skills learn from their executions. Interesting approach to bring this fully local! A bit unfortunate that the RAM requirements will lock some Macs out, but I guess that's not easily changeable right now.

aiagenta2z•about 1 hour ago

So How do you prevent the continuously fine-tunes itself from drifting away from its original capabilities? The idea of training LoRA adapters from user corrections is interesting, and how do you balance personalization vs. catastrophic forgetting?

huyedit•about 4 hours ago

Well, yeah it is fully local. Unless you want to bring in an MCP server from a frontier AI model to explain and give the solution (but that is in a heavy work in process). Thanks for the feedback and yeah the ram do lock some macs out!