At some point people are dead. Really.

Off-topic question: Where is this an "App Store", as this is basically just a curated list off apps? I wouldn't exactly call it a "store". I have an approved ChatGPT App myself, but those do not surface anyway on the chatgpt.com domain. So, this isn't a "store", but a "curated directory". Calling this a store is misleading to a lot of us developers as you can see in the openai forums on this topic, where you find a lot of confusion around this. People put a lot of energy into developing a ChatGPT App, just to find out, they are completely on their own afterwards.

> Using the agent to keep asking questions about pieces of the code I don’t understand instead and pull up relevant documentation and PRs.

I like to do the opposite, asking the LLM to give me relevant follow-up documentation, like the actually docs, where I can read and understand things myself. Data structures, techniques, etc. I still like to read that from the authors, much easier and trustworthy to grasp.

I do this too. LLMs are amazing at finding weird trivia deep in the docs. But you have to go check the original. The machine is often correct-ish.

Claude needs a watch, that's all. Would in itself a 100% improvement.

I am using Withings in combination Tredict. Both GDPR-compliant.

Using Cortecs.ai too in combination with DS4Pro and Mistral Viba as harness, but unfortunately DS4 on Cortecs is the opposite of cheap. So I just use it for privacy centric tasks.

If DS4flash works for your case, then https://tensorix.ai/pricing is offering at pretty much the same rates as deepseek themselves, with EU data residency and guarantees.

That is not correct. I talked about Pro. Cortecs.ai is routing to Tensorix btw.

DS$ Pro on Tensorix. That is not exactly cheap. Input:$1.75 / 1M tokens Output:$3.50 / 1M tokens

Yep, that's why I said, if DS4Flash works for you.

From what I've read online, people have reported that DS4Flash-xHigh works even better than DS4Pro-xHigh .. so, you can try. No harm in trying :)

We had too much Gnutella. I am in search for a locus to us. Now. SCNR

Google is sampling results/views, first spitting out a few and testing, then some more. If people regularly visit impressions/results, then it becomes more trusted and the sampling is widened. Saying: I am not too concerned with this esoteric blog article. The audience of the "poisoning" was probably just "one guy".

That's not how AI Overviews work.

That's what you think. It does. The AI results are steered.

"For example, Ray says it looks like Google and ChatGPT might be quietly removing companies from its AI answers when it suspects they're promoting themselves."

What? So AI answers are empty thereafter. Seriously, how can this be a good idea? At some point a company has to promote itself.