Why “Looping” is being discussed
The most recent Hacker News stories and comments contributing to this topic's mentions.
Any idea why Alibaba might ship a model while aware that it has this defect when it is so easy to fix? Is this looping tough to fix by changing the training?
by HarHarVeryFunny · Nov 3, 2026
I pretty much got that idea when reading the post, on how it didnt have improvements on a Gemma 270M model which didn't have any looping issue. However, it still made me look at…
by ad1ttya · Nov 3, 2026
You are right, if you literally just read a one paragraph description you will get less details than reading the whole post, but most of us read more than just the one paragraph…
by tedivm · Nov 3, 2026
Mainly due to the looping. Before the edit, 93% of MATH-500 answers hit the 32k token limit, compared to 33% after. With 10 and 25 forward passes, looping barely decreased (87%…
by namanbnsl · Nov 3, 2026
> For Qwen, the model fixed a looping bug that may have been known apriori It was included in the prompt itself. The authors say they used claude code for the experiment, and cl…
by porridgeraisin · Nov 3, 2026
Respectfully to the authors and to everyone here, I ask you to actually read the paper before losing your mind, or at the very least plug it into Claude. It is a cool project bu…
by yurimo · Nov 3, 2026
Interest
Proportion of Hacker News items mentioning "looping" over time.
Mentions
Total number of Hacker News items mentioning "looping" over time.
Looping may refer to: Read more on Wikipedia