Always here to rain on any otherwise sunny day 😎

Yes, actual typos. LLMs don’t perform spell checks. Yes, they can “spell check” your inputs, but that isn’t what is actually happening. It’s all predictive text, and if they’ve learned to predict that the appropriate word in this context in 98% of cases is Minnesota, but since their dataset includes real human errors, it’s not unrealistic that then the LLM could also conclude that the appropriate word in 2% of cases is “Minneosta” instead, which means given enough output variables the misspelling will appear.

Again, I have personally had LLMs generate output with typos, not just factual errors.

Edit: cleaned up a couple very human typos

100% this.

It doesn’t though. Because AI was trained on human data, it contains and can replicate human errors. Its extremely rare yes, especially compared to real human output, but I have personally seen ai make misspellings and other human-like errors in its output.

I’ve said it before, but news companies and magazines like this deserve some of the blame for the proliferation of “fake news.” Monetary needs or not, when they lock legitimate reporting behind paywalls that simply guarantees people are going to get their news from “free” sources instead.

I understand the need for revenue, but another solution should have been found that didn’t effectively turn facts and reality into premium subscription content.

Imo stevia is one of the best of the no calorie sweeteners, but since that entire category is absolutely abhorrent that’s sort of like being called the fastest snail.