Not related to code... But when I use a LLM to perform a kind of copy/paste, I try to number the lines and ask it to generate a start_index and stop_index to perform the slice operation. Much less hallucinations and very cheap in token generation.

The current culture about AI & LLMs is that we are "only" memorizing the Web into model parameters and that a LLM is unable to "invent" new paradigms. Maybe we are under estimating what Unsupervised Learning & RL could provide. Re-inforcement learning is about exploring and finding new ways to accomplish a task and I see no limit here (except the computational resources needed).

There is a paper about : https://arxiv.org/pdf/2405.18719

Content semantic maps allows to visualize content of a website in a 2d space. It allows new kind of usage : competitor analysis, conversion visualization, content gap analysis.

Keywords recommendations are refreshed every night.

You can expect some fluctuation depending of several factors (search queries extracted from Google search console etc.)

XLS Keyword export allows up to 10000 records extraction.

So true!

Huge work! That's awesome! The power of photoshop for Linux. No install. Supra fast! Wow!

Good job ! Please add something about namespaces.

It’s on the roadmap!

And composer!

> With this company you end up $100 (or whatever) short and you surrender your data for it to be sold to ... .... insurance companies and whatnot.

False ! Source : https://www.23andme.com/about/privacy/

We will not provide any person’s data (genetic or non-genetic) to an insurance company or employer.

Some great things about companies that you can always count on:

- They never change their terms of service

- The demand for constant growth never causes them to reconsider ethically dubious revenue streams

- They never get acquired

- They never ever get hacked, and even if they do, the insurance compamy would feel immoral to buy the hacked data dump

- they never fail and liquidate assets in a hurry

Also, does anything prevent them from selling your data to a middleman who then sells it to an insurance company?

Then why do they hold onto it instead of destroying any record after transmission?

Because it's an asset, and they are there to make money. Not because they are doing it out of the goodness of their own heart.

You can't take back information.

Curious. Is that binding forever? Are they not allowed to ever change that and then retroactively give out data?