Excellent, thanks for the explanation!

. Gemma and Qwen I run locally on a strix halo framework desktop

So, CPU only?

nanogpt

Do you know how nanogpt compares with openrouter? Why did you pick nanogpt?

How do you get your LLM credits? Or do you run Gemma and Qwen locally? With which hardware?

You can use opencode with a lot of different setups though, you don’t need to go for their subscription model.

Thank you!

What hardware do you use? How fast is it?

Ascorbic acid has two enantiomers. Only one of them is “vitamin C”. I’m not sure if this is what she’s referring to, though.

In another interview (in French, sorry), when talking about beta-carotene, she says that a substance isolated from its natural environment (other molecules, cells, etc.) and replaced with a pure, synthetic version could have very different biological properties.

Honestly, I think we still know very little about this. This research is about strong statistical associations. A lot more research is needed to understand the exact biological processes.

Here’s the press release from INSERM, which is likely a better source: https://presse.inserm.fr/en/colorants-conservateurs-trois-nouvelles-etudes-pointent-des-liens-entre-additifs-alimentaires-et-risque-accru-de-cancer-de-maladies-cardiovasculaires-et-dhypertension/72881/

Start by finding a general consensus over where we should go, the rest will follow.

That’s true, but there are also massive economies of scale when you can afford the big Nvidia gpus and share them among many people.

I agree. I use openrouter myself.

In general I agree with you, but llms are the one exception where it’s not practical and not cost effective to run them locally. If you want to use them, the better option is by far to pay someone for the service.