Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Halluminate (YC S25) – Simulating the internet to train computer use

news.ycombinator.com

Post reply on HN
Print view View original

41–50 of 51 posts

Re: Launch HN: Halluminate (YC S25) – Simulating the internet to train computer use

#41

Post by mandeepj »

fragmede wrote: post #22
mousetree wrote: post #10

Earlier quoted context omitted.

Why are flight bookings the go to example always? For most people, booking a flight happens infrequently, is a non-trivial expense (to your point), and is not that burdensome to do yourself.

It's because most people have done it; and it's infrequent and sufficiently expensive that makes it enough of a pain point to make for a good example. Because it's infrequent, most people don't have a rigorous well-practiced system for how to go about it to get the optimal ticket for their particular circumstances for that flight, and because it can be somewhat expensive, there's a bit of a burden taken on in order t…

> (in incognito mode)

I used to do that, but when I cross-compared with normal mode, the prices were the same.

Re: Launch HN: Halluminate (YC S25) – Simulating the internet to train computer use

#42

Post by jedberg »

mandeepj wrote: post #40
jedberg wrote: post #38

Earlier quoted context omitted.

> and is not that burdensome to do yourself. I don't know about you, but it takes me hours to book a flight if it's for my family, because I'm usually booking a flight, a car, and a hotel, and I have to constantly min-max the costs between hotels on certain days, flights on certain days, and cars on certain days. If it's not burdensome for you, then you're either taking very simple trips or you're so rich that you do…

> I have to constantly min-max the costs between hotels on certain days, flights on certain days, and cars on certain days. I agree it's a burdensome chore! Just wondering - your hotel stay can't be less than the days between your flight. For car, one can manage to cut down with Uber/public transport, but still turns out to be expensive than a rental car.

> your hotel stay can't be less than the days between your flight.

This is exactly right, and why it's such a pain. Because if I have a bit of flexibility, I have to figure out which flying day is best for prices and seats, and then see if the hotel is more or less between those days.

For example, if I fly on Tuesday I can save $400 vs flying Sunday. But if I want to stay a week, the hotel may not have the following Sunday. So now I have to look an alternate hotel, which may not include parking like the first one, and so on and so on. There are so many variables that can all change based on the day of arrival and departure.

We used to have travel agents for this (and still do!). But I've used travel agents, and I've used (other people's) personal assistants, but no one ever gets it right. I only trust myself, my wife, and my sister in law to get this right.

Having an AI agent that gets this right would be incredible.

> For car, one can manage to cut down with Uber/public transport, but still turns out to be expensive than a rental car.

If I'm getting a car it's usually because it's a place where Lyft and public transport won't work. Otherwise I always default to public transport and then Lyft if necessary.

Re: Launch HN: Halluminate (YC S25) – Simulating the internet to train computer use

#43

Post by BobbyJo »

Had this exact idea recently, applied to various software tooling. I think agents of all types are going to follow a similar path to self-driving cars: first 80% comes in a big boom, and the last 20% comes over a decade of training and simulations.

I think each agent use case is going to need a simulation for its reward to eek out the last 20%.

Edit: Realized I forgot to say Great Work! Looks Cool!

Re: Launch HN: Halluminate (YC S25) – Simulating the internet to train computer use

#44

Post by wujerry2000 »

BobbyJo wrote: post #43

Had this exact idea recently, applied to various software tooling. I think agents of all types are going to follow a similar path to self-driving cars: first 80% comes in a big boom, and the last 20% comes over a decade of training and simulations. I think each agent use case is going to need a simulation for its reward to eek out the last 20%. Edit: Realized I forgot to say Great Work! Looks Cool!

Self driving cars are a really good place to derive intuitions. Robotics as well!

Both those spaces are still optimizing on the last mile performance gains that get exponentially harder.

The good thing about computer use is building software environments are faster and also more repeatable, so hopefully we see quicker improvements here. :)

Re: Launch HN: Halluminate (YC S25) – Simulating the internet to train computer use

#47

Post by reactordev »

wujerry2000 wrote: post #18
zebomon wrote: post #12

This is very interesting. I think a lot of people may be quick to overlook the value of such simulators when thinking about AI agents at the extremes. (Either they're not good enough to trust or they're so good they'll leapfrog over any economic value here.) My own experience makes me lean toward thinking that the truth is somewhere in the middle in this situation, and that simulators like these will be valuable. I'v…

Computer use agents are starting to perform well on websites/apps that are in their training distribution, but still struggle a lot when dealing with tasks outside their distribution. A big reason why is because many more niche/enterprise applications are really hard to test on in the real world, hence the need for sims! re: labs doing this internally. They definitely are! However, the scale of sims buildout is going…

Conway’s law strikes again…

Re: Launch HN: Halluminate (YC S25) – Simulating the internet to train computer use

#48

Post by wujerry2000 »

sandGorgon wrote: post #46

this is very cool ! i contribute to an opensource mobile browser (github.com/wootzapp/wootz-browser). would love to have it work in Westworld if it makes sense for you folks.

Lets do it! There's a cal link on our website if you wanna chat more

Re: Launch HN: Halluminate (YC S25) – Simulating the internet to train computer use

#49

Post by wujerry2000 »

nasmorn wrote: post #45

This is very interesting but I would worry if this proves to be an important part of the solution, why would Expedia not release a sandbox that returns validation if agent use becomes valuable for them.

This is a really important question.

I definitely think as companies begin optimizing for an "Agent first" economy, they will start figuring out how to optimize their sites for agent traffic.

They definitely could do this themselves, but I imagine there will be some engineering work/expertise around building RL envs that they might want to partner with an external provider to do it.

ALSO the value of Westworld isn't any standalone env but many stringed together for long trajectory workflows. That is why they may be inclined to work with another provider to do it.

Those are just our thoughts though, will see how the market plays out

Post reply on HN