Earlier quoted context omitted.
Like it or not I think "agents browsing the web" is the inevitable near-term future. Some agents will be malicious, many will not. In 2036, HN posters will be complaining about how such-and-such site only works with closed proprietary AI agents, and how their creaky old Mac M5 running Gemma 3 under Ollama can't browse the site properly because it doesn't follow the 2029 RFC XYZ for agent compatibility that nobody eve…
Sure, lets say I eat up all of that and agree with you: How does this website help/not help? Agents already read HTML perfectly fine, saying "Well, you don't serve markdown so this obviously is bad for agents, you're only serving HTML" doesn't really feel like it's contributing anything either in protecting against malicious agents, or how the website only work for some agents but not others.
Scan your website to see how ready it is for AI agents
171–180 of 190 posts
Re: Scan your website to see how ready it is for AI agents
#172Earlier quoted context omitted.
Like it or not I think "agents browsing the web" is the inevitable near-term future. Some agents will be malicious, many will not. In 2036, HN posters will be complaining about how such-and-such site only works with closed proprietary AI agents, and how their creaky old Mac M5 running Gemma 3 under Ollama can't browse the site properly because it doesn't follow the 2029 RFC XYZ for agent compatibility that nobody eve…
This still doesn't really answer my question, though. This is like telling me my old blog posts can't be parsed by your regex. 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.
Re: Scan your website to see how ready it is for AI agents
#173Shit I scored a 25. I have some work to do to get it to zero.
Re: Scan your website to see how ready it is for AI agents
#174AI industry: "AI agents will soon be able to do any white-collar human job!" Also AI industry: "Please make sure your website is adapted so that AI agents are able to use it."
Seriously, why help an industry that we all know doesn't care and will still scrap your site regardless? The least they can do it put in some minimal effort without expecting everyone to bend over for them.
Re: Scan your website to see how ready it is for AI agents
#175Earlier quoted context omitted.
In a well functioning system, the incentive to make money is somewhat aligned with the incentive to create value for other people.
This is probably your point, but we are not in a well functioning system.
Re: Scan your website to see how ready it is for AI agents
#176Earlier quoted context omitted.
Businesses are generally in the business of serving human customers, not AI agents. Furthermore, if AI agents are so smart, surely they can figure it out for themselves.
Not really, business websites are generally in the business or serving user-agents like browsers that then convey the information to users. If I tell Claude to go search the web and find me a bunch of links to the websites of restaurants in my neighborhood because I want to try something new do you think the restaurant wants to be on that list?
Re: Scan your website to see how ready it is for AI agents
#177Earlier quoted context omitted.
> if adopting a standard is actually a negative for websites, because it will separate the site from its users, sites will obviously not do it. Not that I believe this will be how the future turns out, but what if the main users of websites end up being agents? Then adopting the standard ends up being a requirement for survival instead of something negative. Hopefully and ideally we don't end up there, because then t…
Curious, in this world, what are the people doing? Is it like that WallE floating bed thing? I just find it fascinating people could survive by dissassociating real effort for...
Now imagine doing that but instead jumping 50 years into the future. Surely most of the "highly valuable knowledge work" at that point will look just as alien to us today as today would look to someone from 50 years ago.
Re: Scan your website to see how ready it is for AI agents
#178it's unreliable it says Issue: No WebMCP tools detected on page load Fix: Implement the WebMCP API by calling navigator.modelContext.provideContext() but I already do that. the extension detects them https://chromewebstore.google.com/detail/webmcp-model-contex...
Can you share the website URL?
Re: Scan your website to see how ready it is for AI agents
#179Earlier quoted context omitted.
Not really, business websites are generally in the business or serving user-agents like browsers that then convey the information to users. If I tell Claude to go search the web and find me a bunch of links to the websites of restaurants in my neighborhood because I want to try something new do you think the restaurant wants to be on that list?
I would say that the restaurant would be wasting its time and resources by catering their website to hypothetical customers who are choosing to use inferior and overly engineered methods to find information about their physical surroundings out of technological fetishism. But that's just me.
These AI tools are taking over as the main search/discovery vector for websites. Engaging with it is just basic SEO. This isn't really that complicated.
For content or media sites it's a different story. But most websites direct people to commercial transactions, and that's the group I'm referring to.
Re: Scan your website to see how ready it is for AI agents
#180Earlier quoted context omitted.
Curious, in this world, what are the people doing? Is it like that WallE floating bed thing? I just find it fascinating people could survive by dissassociating real effort for...
Imagine going back 50 years, and without your knowledge of computers, offices and more. Being exposed to the world today with the knowledge and experience from 50 years ago, surely just a typical corporate office would look weird, inefficient and strange. "What do you mean you just write electronic letters all day, how is that work?" someone might ask. Now imagine doing that but instead jumping 50 years into the futu…
The dissassociation is the same confusing/confounding thing.