Yeah meat is another dimension, as is potato. So we're up to 4 dimensional breakfast latent space. I hate to think what's in the dark breakfast black hole of that 4 dimensional latent space...
I feel like there's a lot of unexplored area in the carb-soaked-in-egg category that French Toast fits into. The major analogues being chiliqiles and matzoh brie. I recently did something like french toast bites where I cubed some sourdough bread, soaked it with egg and fried it up with small pieces of bacon mixed in. But what if you did that with a glazed donut? Or a waffle?
[edit] just also why this post touched my heart - I think form is as important as ingredients whenever you're dealing with relatively few ingredients. I have a breakfast I particularly love making that's just hash browns, egg and cheese. But the trick is, you griddle the hash browns, then flip them and smash them on griddled cheese, then crack an egg on top while the cheese fries and flip the whole thing again. The result is a crispy potato pancake where one side is fried cheese and the other is embedded fried egg. The same 3 ingredients, but it can be held in hand and it's got the perfect balance in each bite.
i've done the french toast pizza and it wasn't bad. not sure if it was worth the effort. maybe there's an ideal type of pizza or combo of toppings that makes this spectacular. either way it's worth trying once just to say you did.
Also re: "I spent longer arguing with the agent and recovering the file than I would have spent writing the test myself."
In my humble experience arguing with an LLM is a waste of time, and no-one should be spending time recovering files. Just do small changes one at a time, commit when you get something working, and discard your changes and try again if it doesn't.
I don't think AI is a panacea, it's just knowing when it's the right tool for the job and when it isn't.
Anyone not using version control or a IDE that will keep previous versions for a easy jump back is just being silly. If you're going to play with a kid who has a gun, wear your plates.
Once, I told a friend that it was stupid that Claude Code didn't have native IDE integration. His answer: “You don't need an IDE with Claude Code.”
I've begun to suspect response that this technology triggers a kind of religion in some people. The technology is obviously perfect, so that any problems you might have are because of you.
I find that I vastly prefer Gemini CLI to antigravity, despite the latter being an ide. Others feel the opposite. I believe it comes down to how you are using AI. It's great they both options exist for both types of people.
I don’t think it’s “just” that easy. AI can be great at generating unit tests but it can and will also frequently silently hack said tests to make them pass rather than using them as good indicators of what the program is supposed to be doing.
> AI can be great at generating unit tests but it can and will also frequently silently hack said tests to make them pass rather than using them as good indicators of what the program is supposed to be doing.
Unit testing is my number one use case for gen AI in SWE. I just find the style / concept often slightly different than I would personally do, so I end up editing the whole thing.
But, it’s great at getting me past the unpleasant “activation energy threshold” of having a test written in the first place.
Yeah it’s not accurate at all. Not the OPs fault but the purpleair sensors are placed by users. Right now it says fidi is 9° warmer than haight. Plausible, but it could also be the only 1 sensor reporting from fidi is on a balcony near a drier vent.
> "Walking and biking environments result in ghettoes"
I must admit this viewpoint is one I have never seen before! Instead I've heard many arguments that bike lanes and pedestrianization are forms of gentrification, but resulting
"ghettoes?" +1 for creativity!
Yes? Bikes are an incredibly segregating means of transport. They are inherently limited in range, and they are largely incompatible with any other transit mode.
So you create an environment where all the housing within bike range from good jobs is unaffordable for most people.
And the most democratic mode of transport? Cars. They provide far greater accessibility.
You are spot on about segregation. Yes, walking and biking are for undesirables. The suburbs are built for cars and cars only. Poor people (African, etc) can't afford the large lots, the minimum size of residence, the HOA and lawn maintenance, car required to go anywhere. This is how you can do segregation without violating any laws. Usually, most people don't admit that these are the real goals. I'm surprised that you are openly admitting that segregation is what we want. I guess times are changing!
So you're saying that bicycles have caused our land use patterns to be inequitable? I would say I agree that transportation modes have made land use allocations in western society problematic, but again you are very novel in being the first person I've ever met who attributes those issues to people riding bicycles.
No, bicycles are more of a symptom. They are not the sole cause, of course.
The actual root cause is over-centralization, where the only jobs worth having are concentrated in downtowns of a dwindling number of cities. These downtowns are always congested, and bike lanes are one way to make it more tolerable. But if you can afford an apartment, of course.
Bike lanes near Wall Street are an iconic example. If you're using them, then it's highly likely that you're a multi-millionaire. Or maybe you inherited a rent-controlled apartment.
Cars historically were a great equalizer. Sure, your CEO was likely driving a better car, and living in a better house. But they were stuck in the same traffic along with you. And this _was_ a factor when deciding on the next office location: "Hm. I really hate the commute, perhaps our next office should be in a bit less congested location?"
And this is reflected in actual research: https://pmc.ncbi.nlm.nih.gov/articles/PMC4938093/ - "For the USA, we observe an exponent βUSA ≈ 0 indicating that the density of jobs is independent from the skill level in the USA. For the UK and Denmark, we observe a non-zero exponent with βUK ≈ 1/2 for the UK and a larger value for Denmark βDK ≈ 0.8. These results indicate that the density of jobs decreases with the skill level, more in Denmark than in the UK."
Ok most of what you're saying makes sense, but having gone to bike lanes in lower manhattan it seems like it's a lot of food delivery people 24/7 with the normal new yorkers you'd see on the subway during commuting hours. From a humanistic perspective it seems like it's a good thing to ensure that delivery drivers aren't killed by motor vehicles and have the ability to not conflict with sidewalk pedestrians? As a driver I would prefer they're not in my lane.
> Cars historically were a great equalizer.
I suppose we'll agree to disagree on this one, there's like a bajillion books that assert the opposite so I will let those and the intertubes do the talking.
As it relates to the study, I'm a little confused how it relates to the above discussion. Is this a good or bad thing to have density of jobs relate to skill level? Wouldn't the historic development of these cities with thousands of years of human civilization in Europe vs. relatively recently developed US cities be a confounding factor in exploring land use patterns?
> Ok most of what you're saying make sense, but having gone to bike lanes in lower manhattan it seems like it's a lot of food delivery people
Yes, I should have mentioned that I specifically meant people using bike lanes for commutes. Bike lanes for work or for recreation are a totally different story, and I have nothing against them.
However, in this case it still reinforces my point: delivery by bike is a luxury good. It still is something that makes living in an utterly unaffordable area more bearable for people who have money.
> I suppose we'll agree to disagree on this one, there's like a bajillion books that assert the opposite so I will let those and the intertubes do the talking.
I'm actually not saying anything that is not an accepted fact in urbanism.
> As it relates to the study, I'm a little confused how it relates to the above discussion. Is this a good or bad thing to have density of jobs relate to skill level?
No, it's not good. This means that good jobs force people to move closer to the centers of their concentration. This automatically reduces opportunities for other people.
> Bikes are an incredibly segregating means of transport.
A bike costs on the order of a few hundred dollars; there's essentially no barrier to entry.
Comparing them with cars on this metric is laughable. Must be 18 or so and able bodied, obtain an expensive license, purchase the actual very expensive vehicle, pay for constant upkeep in insurance, fuel, repairs, and risk serious accidents. All of this is an insane barrier to entry.
> They are inherently limited in range
Yeah, to like a radius of 5km or so, on the low end. That's quite a bit in a city.
> and they are largely incompatible with any other transit mode.
Kind of, but not really? Between e-scooters, rental bikes, and bike garages at train stations, this really is just a matter of proper infrastructure in the end. I don't get the relevance of this anyway.
> So you create an environment where all the housing within bike range from good jobs is unaffordable for most people.
And where exactly is this place you describe where everyone commutes exclusively by bike? Ooops, right, it doesn't exist, never has, probably never will. So you're just making stuff up.
I mean, it is a cute little theory, but it has zero relevance to the world we've built or ever plan to build.
Or maybe it's a strawman, implying that someone somewhere has claimed that we should only commute by bike? Again, cute, but nobody says that. Adding public transportation to the equation neatly eradicates your entire made up theory.
> And the most democratic mode of transport? Cars. They provide far greater accessibility.
I adore your conversational technique of adding positively charged words like "democratic" and "accessibility" without any justification or explanation, just to make it seem like you have an argument. "The democratic, accessible and green coal power plants." I'll add this technique to my list of common fallacies, thanks.
> Comparing them with cars on this metric is laughable. Must be 18 or so and able bodied, obtain an expensive license, purchase the actual very expensive vehicle, pay for constant upkeep in insurance, fuel, repairs, and risk serious accidents. All of this is an insane barrier to entry.
Just wait until you hear how much transit costs!
> And where exactly is this place you describe where everyone commutes exclusively by bike? Ooops, right, it doesn't exist, never has, probably never will. So you're just making stuff up.
Who said anything about exclusivity? Please point out with a hyperlink.
> I adore your conversational technique of adding positively charged words like "democratic" and "accessibility" without any justification or explanation, just to make it seem like you have an argument.
I provided a link in this thread. Go on, dispute it.
Like everything in LLM land it's all about the prompt and agent pipeline. As others say below, these people are experts in their domain. Their prompts are essentially a form of codifying their own knowledge, as in Rakyll and Galen's examples, to achieve specific outcomes based on years and maybe even decades of work in the problem domain. It's no surprise their outputs when ingested by an LLM are useful, but it might not tell us much about the true native capability of a given AI system.
reply