Conspicuously missing: why should I care?
I have reduced my online presence to much less than it once was partly because I don't want to feed this machine training data that I've worked hard to make for a human audience.
I have reduced my online presence to much less than it once was partly because I don't want to feed this machine training data that I've worked hard to make for a human audience.
Like... yeah, no shit; I didn't build it for your regex. It's not the target audience.
Plus, isn't the appeal of LLMs broadly that they can do somewhat-useful things with mostly-arbitrary input (if you ignore the risk of prompt injection)?
They can definitely read HTML, but they do better with more structure. I proposed in a sibling comment for example that the "reader mode" feature in browsers might be a great LLM-compatibility feature to reduce all the HTML token noise. Or exposing an HTTP API with an OpenAPI schema and a proper sitemap and an RSS feed. For example fetching from an RSS feed can be exposed to the LLM as a "tool" that it can call.
Though this is undermined somewhat by stories like this one[0], where an AI runs a "slow life" store catering to a lifestyle that specifically tries to disconnect from technology.
It's incredibly perverse.
[0] https://andonlabs.com/blog/andon-market-launch