I found that Deep Research mode in Gemini was able to give me a well planned 4 day trip to a major city.
I told it my preferences and of the group members, where we arrived and departed, at what times. I gave it my itinerary and then asked it to plan two new itineraries and also suggest a location to book a hotel that was convenient for the early flight on the last day.
I went away for 20 mins and gave me a 20 page document with a good summary and decent options. I did choose some of the activities it suggested.
I did this 10 months ago. It’s probably better now.
But Gemini has access to google maps, so it can estimate travel times, and know which lunch places are near which sites and which hotels have good reviews. So if you want AI to work for travel panning you need to ground it in good data.
I used LLMs last year to plan an multiple week itinerary through Japan with the family, I wasn't super happy with the result so I tweaked it but they provided a useful template and some surprising ideas.
As you guessed, there's a ton of info in the training data on this topic, but there's some value in being able to see it on one place with different options.
I think your experience with that trip echoes mine in a lot of areas. It’s a decent start. It takes care of some of the initial blue sky thinking to lay the groundwork. The problem is I think that’s the funnest part of a problem and I hate working on the details… it takes most of the creativity out of most problems as if it was drudgery, while leaving me to do the nitty gritty, which I consider the actual drudgery. I just don’t see LLMs’ contribution to tasks like this being anywhere close to being worth what they’ll cost after the VC subsidies run dry.
It’s really one of the most flabbergasting things about discussing LLMs with the naysayers.
There are a lot of extremely legitimate concerns, like the environmental impact and so on.
But I just laugh when they point out that LLMs are merely clever regurgitators of their previous inputs… as if this isn’t how we as humans operate nearly all of the time. People realllllllllly want to think they’re special snowflakes.
They do research,
Pick destinations led by their own experience/likes/dislikes
Compare to other guides
Plan itineraries so they can get there
Check and share
Ask an LLM to plan a trip:
It takes the prompt and continues it based on weights in the training data. If there is no data it picks the most likely thing (maybe made up). If there is it’ll mostly add things from that data. Maybe it’ll make tool calls and pull in data that way too but you can’t actually trust all the details.
These two processes are so different, it’s important to understand how they work, which is nothing like a human.
I think even if what you say is true, it doesn't address parents' point that both humans and machines regurgitate what they've consumed.
But I'd also want to point out that the way you're characterizing an LLM planning a trip doesn't have any structure to it, which indicates that in your scenario you're not using any kind of harness. I've been amazed at how capable even 30 billion parameter models are when I put them inside of a harness that provides structure and task management. If you consider that scenario, especially with the ability to search the web and use skills, suddenly the LLM looks a lot more like what the human process looks like.
I was able to bully an LLM into giving me a 2wk travel itinerary to Somalia. My stipulations were that I wasn't interested in spending any money, so I'd walk everywhere and sleep outside. Getting there and back from Boston took some arguing--I initially suggested stowing away in a shipping container which the LLM claimed was too unsafe. We eventually compromised on sailing as a reasonable alternative. It planned out a whole route with marina stops, calculated fuel burn, etc. I told it I don't need any of that I have an anchor and sails, won't use the engine or marinas (claimed I'd forage for fresh water ashore). It seemed fine with that idea, but raised some safety concerns about piracy. It was eventually satisfied with my answer that I'd bring a lot of guns to fend off pirates. Total trip cost including some 200+ cans of Dinty Moore and 50lb bags of rice came to something like $700.
There are plenty of humans who plan trips by concatenating destinations that appear the most frequently in their instagram feed. Not that different from how an LLM does things.
Where humans and (current) LLMs differ the most is their failure mode. A human friend could be bad at planning trips, but that's kinda predictable, we're used to it, we know how to catch that Exception. LLMs on the other hand still have failure modes that come across as really wacky, like, what are they smoking in Mountain View?
Which might actually serve as better evidence of different internal workings at a deeper level, than just parroting well-known superficial features of stochastic whatevertheysay.
Yes, it can be confusing if you don’t read the article. He said he went on a 10 day trip and didn’t take a computer. That is context for why he got a Bluetooth keyboard. I doubt he decided to bring a monitor on the trip.
The UK also has much stricter training requirements prior to being granted a license, among other differences. I don't think we can pin all the differences on the yearly MOT.
Stepping out of pure maths and into engineering we find complex numbers indispensable for describing physical systems and predicting system change over time.
I don’t have a list to hand, but there are so many areas of physics and engineering where complex numbers are the best representation of how we perceive the universe to work.
Who should accept responsibility when a conversion is not as expected?
There are very few ‘lossless” conversions possible if you consider the loss of a data or metadata could affect the result. So if printer did accept a file that needed to be converted, and then during printing and converting they found conversion could lead to unexpected results should they cancel the print run? There is just too much to go wrong in printing already without these extra problems.
The print industry has a long and storied history, and for whatever set of reasons, printers only accept very specific profiles of specific formats.
The problem isn't so much finding the shortest path, but finding the right cost function that adequately matches human satisfaction. Not just distance, not just turns, but also knowing which areas are done, and other small factors.
That is exactly right as anybody who has done the work in a wrong way recognizes.
In a way, the computer science student may or may not have realized that he has stumbled upon one of the biggest problems in software development--the arrogance of ignorance.
Especially with lawn mowers, turns are highly weighted over distance. Also, if you are regularly mowing, then it's not so obvious what has been mowed and what not. So regularization and simplification of the path is even more important than turns so that you can discard whole plots in the to-do list.
Roomba's (RIP) don't have the same memory and turn weight function that humans do, of course.
For an employee the cost function is maximum wage for minimum work. Since at minimum wage, you're paid for your time, this means sweeping as badly and slowly as the minimum the manager accepts.
Hell, given that there is a social safety net, and you'll have costs to do the job (food, public transport, ...) you're probably even better off doing worse than that, and getting fired when the manager is "tired of your shit" or whatever.
Then you'll get unemployment, which is slightly less, but you can invest the time in cooking at home, and you'll eat better and have more money left over.
It's a very cynical view but I kind of agree. In those kinds of jobs, the only rewards for doing the job well and fast is just more mindless jobs of the same type.
It would be usefull if you would receive a benefit for doing the job better or you could leave earlier for the same pay but that is rarely the case, since as you said, employers generally pay for your time instead of task completion (which is rather dumb because it offers bad incentives for both sides).
I have talked about this with some business owners who were getting kinda angree that some employes were not putting in a lot of efforts. In all case they were paying the minimum wage with absolutly zero compensation for doing the job better and/or faster.
I can't decide if they are just stupid or simply corrupt but they really should realise that with a strong welfare state and plenty of similar shitty jobs available, the stick really cannot work all that well and they should really use the carrot a lot more.
But of course those people generally make at least 3-4 times the minimum wage and they feel they deserve the premium because they deserve it and are so much better. Funnily enough, those that I know consistenly do a worse job than their employees at most things and it's obvious they didn't get there by starting at the bottom.
> I can't decide if they are just stupid or simply corrupt but they really should realise that with a strong welfare state and plenty of similar shitty jobs available, the stick really cannot work all that well ...
That assumes the manager level above them isn't doing the exact same thing.
I'm mostly talking about people that don't really have a manager above them or all the freedom they need to organise payroll as they see fit. Restaurants owners, recreation center owner, tradesman, etc.
They really could reward good elements, but treat everyone as interchangeable at the same exact pay rate. They get mad when people don't do as good as a job as they wish and then they get mad when they find another job.
I have many examples, but 2 recent ones where:
- a man who was hired as lifeguard for a small pool was being complained about for not cleaning the thing properly, even though every single similar job do not require this tasks for the same pay level, he left to create his own business with friends and is much happier (even though he doesn't make much more money yet).
- a woman who was hired as waitress ended up doing the vast majority of the work for the other waitress, a woman part owne that was quite a bitch in many ways. The hired woman got paid minimum wage and had to share the tips, even though from what I saw, she is the one who got most of them. The next season, she refused to come back, prefering instead working as a cashier. The woman owner was somehow confused. The hired woman was a strong worker, no reason to slave away for greedy ungratefull owners.
Unsurprisingly, the first business isn't going well (2 year going chronic deficit) and the second one just failed after 4 years. Those people just don't understand the true value of work, because they never had to do as much work themselves. I won't details my connection but they are people I know very well and the link is so obvious to me, but apparently not to them.
But they are failing, so I guess karma is a bitch in the end.
I think that is a bigger impact on writes than reads, but certainly means there is some gap from optimal.
To me a 4k read seems anachronistic from a modern application perspective. But I gather 4kb pages are still common in many file systems. But that doesn’t mean the majority of reads are 4kb random in a real world scenario.
I told it my preferences and of the group members, where we arrived and departed, at what times. I gave it my itinerary and then asked it to plan two new itineraries and also suggest a location to book a hotel that was convenient for the early flight on the last day.
I went away for 20 mins and gave me a 20 page document with a good summary and decent options. I did choose some of the activities it suggested.
I did this 10 months ago. It’s probably better now.
But Gemini has access to google maps, so it can estimate travel times, and know which lunch places are near which sites and which hotels have good reviews. So if you want AI to work for travel panning you need to ground it in good data.
reply