Hacker News Reader

That's an interesting hypothesis but the words we use to express agreement and disagreement haven't changed much.

We don't try to retrieve articles/topics from the model, which would be affected by the cutoff, just asking it to analyze the sentiment or summarize the content provided in a prompt

View on HN

True. It would be interesting to run these same tests on the 7B model to see if trend information changes or not. 7B had a march cutoff so if the aug-dec dip migrated to oct-march (or just disappeared) it would be strong evidence for training/data bias. If nothing else, comparing 7B to 70B would likely be interesting.

edit I realized too late I had the years off. It is pure coincidence of month, not a real data bias. Sorry! I still think it would be interesting to see a 7B comparison but that is just to see how well a small model could spot big trends compared to a bigger one.

yep! And of course the new 3.1 model

Reply on news.ycombinator.com