Hacker News Reader

Hacker News

Comment by theturtletalks | Hacker News Reader

Full thread

theturtletalks

This is what he built:

https://isochronic-passage-chart.netlify.app/

Doesn’t work too well on mobile but looks interesting

View on HN

It is hallucinating many flights in my region, some that never existed (so it is not an outdated data problem).

I also see some logic flaws. It overlooks the option of going to a major hub to access faster aircraft, rather than hopping on local hubs.

Also, immigration and customs are cleared at the first airport you arrive at in the country, not at the last one.

In some countries, you need to clear immigration even while going to a third country, so 1 hour is not enough to do it.

It looks interesting but, like a lot of AI, looks correct but is not. Most of northwestern Canada says you can get there by road. If you look at Google Maps, there's no roads there for quite awhile. I see one highway between Inuvik and Tuktoyaktuk but that's about it.

Reminds me of a fun story. Some 20 years ago when I moved from Fort Frances to Toronto for college, my high school best friend was also going to college in Toronto, and his dad offered to drive us together in his truck with all our stuff in the back. We were saying our goodbyes and my buddies dad said to my dad "We'll get there a lot faster, I found a shortcut!" My dad, confused says "shortcut? there is no shortcut, just highway 1..." and his dad insists he found an alternative route, much shorter by kms and we'll fly up there 6 hours faster! Get into the truck and he pulls out 5 pages of printed mapquest... I assure you, having done it, Sault Ste. Marie to Sudbury via Elliot Lake on logging roads, may look interesting, but not correct, added a good 8 hours to the trip.

It put the chart title directly on top of Australia.

Which just about sums up my experience with using LLMs to code, really (though not with these state-of-the-art models, admittedly) - it's amazing what they can do, but left to their own devices they'll make boneheaded decisions.

I believe thats why they put 'Sydney' as an option at the top to recenter the map.

The real issue with the title is that it doesnt fit in the box!

> it's amazing what they can do, but left to their own devices they'll make boneheaded decisions.

Yeah, the whole "can run for 9 hours on a task" to me is not a positive.

I tend to find if Opus 4.8 runs for ~15 mins on a task, then the end result has gone off in a weird direction at some point, and it needs winding back a fair bit.

And that's with extremely clear direction, literal specification docs to follow, etc.

That being said, having functional code already created beforehand (ie by a human) goes a long way to ensuring the AI model has a path it can build on without making too many dumb architectural choices by itself. Generally.

It's fun and it looks good regardless of whether its 100% correct (It would certainly take me more than 9 hours of work to do better than this). Making these bespoke tools possible for most people is a big deal.

The UI is full of glitches: the legend that's placed right on top of Australia, the title that doesn't fit in the box, the crosshair that doesn't accurate track the cursor, the pixellated fonts along the perimeter, the unreadable colour combinations in the overlay, the rendering glitches along the axes when you flip from tab to tab and so on and so forth.

It's like someone took a beatiful, intricate piece of vintage jewellry and made a slapdash imitation out of cheap plastic.

Yep. People are creating garbage with AI that looks passable at first glance, or maybe acceptable if you have no taste. This is the kind of software we can expect to receive in the next few years.

It is cool, but still weird that it get's very basic stuff wrong like mapping the cursor coordinate to the canvas. There's some y-axis scaling issue.

Doesn't work too well on desktop either! This is decent but it's also an early hackathon set-up - this is something that you can set up on a sonnet model fairly easily (without the weird CSS slop that anthropic models seem to love).

I'm not very threatened by this if this is the dangerous Mythos model - it just seems like a slightly incrementally better sonnet

Reply on news.ycombinator.com