![](/static/253f0d9b/assets/icons/icon-96x96.png)
![](https://lemmy.ml/pictrs/image/d3d059e3-fa3d-45af-ac93-ac894beba378.png)
“Glue is not pizza sauce” seems like a common fact to me but Googles llm disagrees for example.
That wasn’t something an LLM came up with, though. That was done by a system that uses an LLM. My guess is the system retrieves a small set of results and then just uses the LLM to phrase a response to the user’s query by referencing the links in question.
It’d be like saying to someone “rephrase the relevant parts of this document to answer the user’s question” but the only relevant part is a joke. There’s not much else you can do there.
Afaict from reading that (and one of the sources, and its source) it boils down to the fuels’ “RVP levels” (which have an impact on volatility and the amount of VOCs given off) being past a particular threshold. E10 is also past that threshold, but it has an exception that E15 doesn’t have. However, by that same measure, E15 is less volatile than E10.
The author also expressed concern about expanding corn production as a result of expanded E15 and that there haven’t been sufficient studies on the impact of E15 on the environment (particularly in the summer months). But that’s also paired with a statement saying that “consumers don’t want E15,” which detracts from the previous arguments; if true it means their impacts, if any, would be minimal.
I didn’t read every link from that page but none gave a better reason.
My takeaway is that it sounds like we don’t have any data showing that E15 is worse than E10, so the obvious move is to actually start funding those studies.
I also found https://foe.org/blog/2012-05-understanding-e15/ which is very anti-E15; however I wasn’t able to verify their claims because none of the linked articles loaded for me.