Hacker News
points by rhdunn 4 days ago | 0 comments
It's fairly straightforward to write a function that detects looping output -- I wrote one for promptfoo in [1].

For training you would need to hook it up to a LoRA training harness, identify the looping weight direction, and adjust the weights accordingly. I've not (yet) looked into how to do this.

[1] https://news.ycombinator.com/item?id=48555634

[–] latentsea 4 days ago
Probably this is the type of thing the 'Swift' or 'ThinkingCap' variants of the Qwen models did I guess. Identify the 'actually', 'but wait' directions and minimize them...
Hacker News