I find it helpful to think of LLMs as reflections. If you can talk like an expert mathematician at the model it will respond like one. While Terrance's first prompt looks trivial I expect a first year Uni student would be hard pressed to provide something that good.
I guess it is kind of the inverse of the "you are an expert mathematician" prompt engineering of gpt3.5. Since no one ever says that to an expert mathematician when they are doing expert math the model immediately reflects that it is not an expert mathematician.
Isn't LLM doing something like argmax{x} P(x|context) where x is the next word, and context is the words before including your instructions? Thus, the LLM output is heavily depending on your instructions, and if you input an expert context it would produce an expert result. Consequently, domain expertise has a significant bearing on what you can achieve from LLM.
It seems too concise to be AI. My (conscious) heuristic for AI writing is how much context is squeezed into a sentence. LLMs seem to be pretty bad at the kind of elegant compression of meaning humans can do when they have done a lot of writing practice.
If I had to guess, I would say this is the human summarised conversation(s) with a bot.
Sorry if my speculation was bad! When I wrote it I meant it as a compliment. Raw LLM output is awful and really needs a human to "translate" the useful content to something worth reading.
I guess ask the bun people why they translated from zig to rust. I think it was essentially because rust guarantees a set of bugs can't exist so over medium to long term timeframes you end up with less technical debt.
Significantly cheaper than comparable models if you are using openrouter [0]. Just yesterday I spent roughly 13 cents centering some divs using Deepseek in a personal project. It would have been north of $1 to do that with a US frontier model.
Flash will get their faster then the sonnet tier which involves reasoning which is slow. And you don't need reasoning to center divs.
The sonnet tier sits below claude or chatgpt in terms of price but costs so much more than free models. If you are breaking downtasks now I'm not sure that 13 cents is worth it.
You should try out the cheaper models first. I find Deepseek v4 models pretty comparable to sonnet 4.6 but at a fraction of the cost. You might find you just don't need to use the American models at all.
That first map seems to map quite closely to koppen climate zones across the continent. Its hard to say whether the climate is decisive here because climate is a big influencer of urban design. However, its interesting that in Australia its the two Mediterranean climate cities (Perth and Adelaide) which frequently get labelled as worse for tree cover compared to the sub tropical east coast cities.
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.
People are not (yet) aware what has been making everyone fat, but ozempic is making it harder to ignore that ultraprocessed foods are the culprit. So hopefully this will change.
I guess it is kind of the inverse of the "you are an expert mathematician" prompt engineering of gpt3.5. Since no one ever says that to an expert mathematician when they are doing expert math the model immediately reflects that it is not an expert mathematician.
reply