Live data from Hacker News

Software development with AI is starting to feel like cooking steak

blog.sydorets.com

301–310 of 439 posts

Re: Software development with AI is starting to feel like cooking steak

#301

Earlier quoted context omitted.

All metaphors break at some point. However, your example actually proves the point. How many people who want a good steak know how to identify a high quality cut? Do they even know where to buy a high quality cut? What the different cuts are and whether they want rump, sirloin or fillet? How many kitchens have a meat thermometer? How many home cooks know how to use it and what the right temperature should be? How man…

My point is that steak is very, very, very far from the hardest to get right. I'm not going to contest your argument about how hard it is to get right, I'm going to argue that innumerable other dishes are vastly harder. Because the quality ingredients are harder to find, because they involve far more steps, each of which is harder to judge, because often good recipes or instructions simply don't exist, etc. etc. etc.…

A steak is hard because the processes to make it are physically contradictory (crust vs interior). Its hardness is a microcosm for why cooking in general is hard. There is a profound value in that, in that if you can handle a single steak (to some standard of satisfaction) then you will have the general skills to handle recipes involving even more steps. It becomes a reduction argument. It is true that the more moving parts/steps/interactions a dish involves the hardness grows combinatorially. But that is logistical hardness, e.g. managing the complexity of a flavor profile. Soon that amount of multiplication/permutations escapes the realm of any one human being to handle.

Re: Software development with AI is starting to feel like cooking steak

#303
post #250

Earlier quoted context omitted.

Believe me, there's a huge spectrum, from the sweet aroma of freshly ground Brazilian beans to straight up cat piss coffee sold in supermarkets.

No offence, but for some reason some people just can't accept a simple fact: for some people this difference is still not a difference. I've tried good coffee. At least that's what people told ne on multiple accasions where I was taken to "the right places" in multiple countries. On two sides of the globe (Brazil and Vietnam if we are talking about producers, not to mention countries that import the beans). Thing is:…

All coffee tastes like cigarette ash to me. Similarly, I have been to places that people rave about. My buddy used to run a coffee shop. "Your beans were overcooked"; no, not it. There is something innate to espresso or something. Smells amazing. Tastes like ash.

Re: Software development with AI is starting to feel like cooking steak

#304

I take the point, but I think the author picked a poor analogy. Cooking even an excellent steak is actually not that hard. In fact, I'd argue that it's among the easiest things to master/make at a top level quality at home. Does it require some modicum of attention and understanding? Sure. But starting with a high quality cut, owning a meat-thermometer, and knowing about reverse searing is about all it takes to relia…

I'm more of a coffee nerd than a steak aficionado but I've often made the comparison between those two. In both cases, the enthusiast considers their skill in making coffee/cooking steak to be a differentiator and they immerse themselves deeply into the process, skills, and tools. But for both coffee beans and steak the most important factor for a good end product is starting with high quality inputs. In other words,…

I strongly disagree with this on the steak part and maybe the coffee too. Many people pride themselves on buying expensive ingredients and thinking they have the best steak but it actually sucks.

To get good steak you don't need USDA Prime dry-aged steak. You just need USDA choice, picked for a bit of marbling, salted the day beforehand and dried out uncovered in the fridge, then a ripping hot heat source (grill or cast iron etc) to get a good sear on the outside (reverse or not) and a thermometer to hit medium rare on the inside.

Even a modest steak made this way tastes better than a prime steakhouse steak that was doused with salt right before cooking, where you're going to get hypertension immediately yet the meat tastes weirdly unflavorful.

To extend this analogy further, consider making BBQ brisket Texas style. Brisket is a cheap cut of tough, fatty meat. The input quality matters even less there, and it's all dependent on chef skill. Same thing with sourdough bread — 4 ingredients, all outcome depends on skill.

Source: we make an app that teaches people how to cook (https://parsnip.ai)

Re: Software development with AI is starting to feel like cooking steak

#305

I take the point, but I think the author picked a poor analogy. Cooking even an excellent steak is actually not that hard. In fact, I'd argue that it's among the easiest things to master/make at a top level quality at home. Does it require some modicum of attention and understanding? Sure. But starting with a high quality cut, owning a meat-thermometer, and knowing about reverse searing is about all it takes to relia…

The analogy I'd use is using LLMs for coding is like a movie director does for movies. A movie director does not draw storyboards, they ask an H.I. (Human Intelligence) storyboard artists to do that. They don't make the costumes they ask an H.I. costume maker to do that. They don't control the camera they ask a H.I. camera person to do that. They don't usually act, they ask H.I. actors to do that. They don't make the soundtrack, they ask an H.I. composer to do that. They don't edit the video the ask in H.I. editor to do that.

Further, they don't just accept what each of those H.I.s does on their first try. The most visible example is when the H.I. actors don't act exactly as the director wants, they retake the scene. But, the same is true of all the rest. As the "director" they "direct" each of those H.I.s toward their vision.

IT seems similar for coding with an LLM. I become the director. I direct the LLM. I check it's results and if they are unacceptable I re-take with instruction on how to do things closer to what I actually want.

Re: Software development with AI is starting to feel like cooking steak

#306

Earlier quoted context omitted.

Go to costco, buy prime filet. Put it in a ziplock in a sous vide at 130 for an hour. Drop it in corn oil at 425 for 30 seconds. Add some butter and salt. That simple process, suggested by Nathan Myhrvold (former MSFT cto) in the modernist cuisine, produces a filet better than most restaurants.

a filet better than most restaurants. Bad restaurants, sure. It does not hold a candle to any half decent steakhouse.

I went to the second rated steakhouse in NY at the time and got a steak some ten years back. I would have preferred my home-sous-vide by a wide margin. I have only had a better steak twice, and only once from a restaurant

Re: Software development with AI is starting to feel like cooking steak

#307

I take the point, but I think the author picked a poor analogy. Cooking even an excellent steak is actually not that hard. In fact, I'd argue that it's among the easiest things to master/make at a top level quality at home. Does it require some modicum of attention and understanding? Sure. But starting with a high quality cut, owning a meat-thermometer, and knowing about reverse searing is about all it takes to relia…

The analogy I'd use is using LLMs for coding is like a movie director does for movies. A movie director does not draw storyboards, they ask an H.I. (Human Intelligence) storyboard artists to do that. They don't make the costumes they ask an H.I. costume maker to do that. They don't control the camera they ask a H.I. camera person to do that. They don't usually act, they ask H.I. actors to do that. They don't make the…

You can always tell a director who does do their own storyboards. The film is always visually bats**. In a good way.

I'm looking at you, Guillermo del Toro.

Re: Software development with AI is starting to feel like cooking steak

#308
post #12

I do not appreciate when authors use the royal "we" to speak for all software engineers when admitting to low quality-control standards. I suspect that it is an attempt to broach an uncomfortable topic through vulnerable self-disclosure, but we need to be serious about admitting when there is a problem somewhere. "Bugs" are not any more cute or fuzzy or entertaining or harmless than the engine "gremlins" that haunted…

> [...] but we need [...]

You did the same thing you criticize the author for doing.

Re: Software development with AI is starting to feel like cooking steak

#309
post #304

Earlier quoted context omitted.

I'm more of a coffee nerd than a steak aficionado but I've often made the comparison between those two. In both cases, the enthusiast considers their skill in making coffee/cooking steak to be a differentiator and they immerse themselves deeply into the process, skills, and tools. But for both coffee beans and steak the most important factor for a good end product is starting with high quality inputs. In other words,…

I strongly disagree with this on the steak part and maybe the coffee too. Many people pride themselves on buying expensive ingredients and thinking they have the best steak but it actually sucks. To get good steak you don't need USDA Prime dry-aged steak. You just need USDA choice, picked for a bit of marbling, salted the day beforehand and dried out uncovered in the fridge, then a ripping hot heat source (grill or c…

One way to phrase that would be to say that you have a vested interest in supporting the idea that end user skill is more important than ingredients since you sell a means of improving end user skill. Not sure if that's a source or a conflict of interest. I'm not saying cooking a steak is easy or hard, I'm saying that you are not creating quality when you cook a steak; the maximum attainable quality is capped by the ingredient. It's like the "I made this" meme.

You're arguing against a strawman on your other points since I didn't make a generalization about all cooking and wouldn't have listed sourdough or brisket in the analogy.

Re: Software development with AI is starting to feel like cooking steak

#310
post #224

Earlier quoted context omitted.

I wonder if something is lost to translation. Cooking a stake could be the simple act of putting the steak in the oven with basically zero seasoning with a thermometer and then wait until medium rare with some optional searing. It could also mean trim the meat, cut into slices, seasoning, and frying/grilling them to each persons personal taste, which include well-done. Perfect grilled steak, especially well-done, is…

is "cooking" here used in some kind of very specific sense? isn't it just a word for "making food", so would include grilling as well?

That was my interpretation, in which there are many ways of cooking of steak. Some will be very easy, while other to methods seems to give many chefs problem (both professional and home chefs). Many people seem for example to associate well-done steak with something that is dry and burned, rather than something that simply takes more work, precision and skill to get right.
Post reply on HN