Hacker News

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, most of the work is being done by the farmers, the processors, and the quality of the raw stock (the cow or the coffee plant). Your job at the very end of that long value adding chain is to not ruin the hard work that others have put into it.

I'm not sure if this analogy holds up in the AI software metaphor that the author of the blog post is making.

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 many home cooks know about reverse searing? Or timing? Or resting? Or seasoning?

Is it all learnable? Sure. But even something as simple as steak has nuance that needs to be learned, equipment deployed to go from "pretty good" to "great", experimentation and trial and error.

Steak is the simplest thing to choose to get started. It's also the hardest to get right.

Building an app is the simplest thing to choose to get started. It's also the hardest to get right.

So, honestly, the whole metaphor stands up pretty well for me, specifically because of your response.

Agreed. I'm an avid cook. Sous vide circulators are cheap now, and so are meat thermometers. Doing a steak well is one of the easiest cooking tasks, to the extent that I won't bother paying top dollar in a restaurant because it's so easy to do restaurant quality at home. I could teach someone to cook a restaurant quality steak in a couple hours and a few practice runs.

I also don't think the analogy will age well.

It might take more than 10 years, but robots will almost certainly master cooking single pieces of meat.

It's substantially harder to reach self driving than it is to cook a "good" steak.

Sure, for probably quite a long time you'll be able to find someone who can cook a way better steak than the best robot, especially because taste is extremely subjective...

You can debate the horizon and the extent, but changes ARE coming.

Change is the only thing you can count on besides death.

> I take the point, but I think the author picked a poor analogy.

He may have missed the point.

AI-generated code does not seem to have parsimony, for one. Generating code is cheap, so there's no drive to condense it. LLMs are not yet good at formulating abstractions to make code smaller, leading to code bloat. It's the same phenomenon that appears when humans modify code they only partially understand by adding special cases to general code.

There are complaints about "elegance", but it's more useful to talk about parsimony. Code bloat is measurable. Elegance is hard to assess.

Agreed. With steak, the main point is to let the quality of the meat speak for itself. Too much input from the cook and you just get in the way of this.

Now it's steak, tomorrow it can be pasta, next year it can be watermelon kimchi.

I was just curious asked chatgpt:

How can I make a really great steak myself? What to look out for, what to do. Give me detailed instructions.

I got a really good answer (including - cut, temperature and reverse searing), so I probably won't even need understanding. (Oh - and yes, I can cook - the answer mirrors what I already know).

Yes, it was a very, very poor analogy, because cooking a steak is a well known and well documented thing where LLMS produce good output. They fail when you get off the beaten path and try to do something that's not "mainstream".

It is a great analogy, as the vast majority of software tasks are CRUD or glue logic. At this point, relatively narrowly-defined tasks are a solved problem with frontier models. It is only more advanced tasks with broad scope and large context that frontier models have more limited results.

The problem is that not everyone can afford/wants to spend on a high quality cut. A good cook can make a cheap cut of meat taste great. There's no single right way of cooking a steak and that can include spices/herbs/marinades/oils/etc.

hehe I always turn mine grey but I have mini bella mushrooms on top

How do you get around the idea of poisoning oneself? Keeping meat part raw feels uneasy.

Am I the only one who thinks the "reverse sear" is like cheating? It takes out all of the skill when you move from the pan to the oven, and I lose all of the fun in learning to be chef.

The ragebait > AI pipeline remains strong

HN has also covered steak cooking before:

Show HN: I Derived a Steak https://news.ycombinator.com/item?id=48691840

https://www.youtube.com/watch?v=rDBNVO7K0kA this is a really good little episode from PBS

To get a perfect steak with nice X-shaped sear marks on both sides:

1. Turn grill on all the way. Close lid. Wait for grill's gauge to reach >400 F (>200C).

2. Put steak on grill. Close lid. Wait 2 minutes.

3. Rotate steak 90 degrees, placing on a fresh section of the grill (not where it just was). Close lid. Wait 2 minutes.

4. Flip steak over, placing on a fresh section of the grill (not where it just was). Close lid. Wait 2 minutes.

5. Rotate steak 90 degrees, placing on a fresh section of the grill (not where it just was). Close lid. Wait 2 minutes.

It's been 8 minutes of grilling. Steak is about done. Stab it with a meat thermometer into the middle part, it should read 350 F (or 176 C) to be medium done (pink in middle).

Tips:

a) Optional but recommended: rub steak with olive oil and steak seasoning on both sides, including the edge.

b) If steak is thicker: add a little more time. If thinner, use less time.

c) If steak is frozen (buy good cheap steaks and freeze to last a long time): add a little time.

d) To cheat, put a little dab of butter on top for the last segment of each side.

e) Leave the steak out for 15-20 minutes to get to room temp before making it.

f) Let it sit on a plate for 8 minutes before serving. It's still cooking, and the juices settle in. You can "tent" foil over it if you want.

g) Don't cut the steak when checking it. "Fast" and accurate meat thermometers are cheap now.

This is for grilling. The stove, broiler, and cast iron skillet instructions are different.

AI is the new rick-roll

I just want to point out this is not a royal "we". It's a regular "we". Royal "we" is when you say "we" but mean a singular person, yourself. Here, the author does actually mean multiple people beyond themselves - like you pointed out, they claim to speak for all software engineers.

At least in my experience, the 'software' people are VPs/management who push and push with short term thinking.

> To build good software with AI, you still have to understand software.

> You need to know what you’re actually asking for, how to judge what comes back, and when the machine is just confidently serving you charcoal.

It's surprising to me this even needs to be written down. Like, obviously still use your brain and think about what the computer is doing. Did you guys think that LLMs were magic?

Article aside, I generally always use the "we" pronoun at work when writing prose. Saying "I" feels too adversarial when talking about negative effects, or too self-aggrandizing when talking about positive effects. For example: "We discovered a bug shipped at the end of the merge window, so we will restart validation with the rollback applied." I think in school they say the business-safe way to write is instead with the passive voice but I just can't do it.

"We all could have done more.": said by every politician. Which is easier: writing good code, or winning a political battle over crappy code? I mean, if you're not capable of coding, and creating an appropriate architecture for the the domain: which course of action gives you the most control over risk management? So yeah most fights about software are about politics and crappy code.

Saying this to set expectations based on having a business license since 1984.

The author didn't say "we (all software engineers)", so the only person including you in his class is you.

Idk, OpenAI themselves released some weird Electron app to replace their native version of ChatGPT on mac https://www.siliconreport.com/openais-chatgpt-mac-update-shi...

It will be a push and pull and I'm curious where we'll be in a couple of years.

I can fly at 100mph if I let AI run loose and with a bit of steering I can get it to output what I'm looking for and generally pass verification and tests.

If I care about the code though, and I want to keep it maintainable, the amount of time and tokens I need to spend correcting and iterating on the output quickly eats through much of the initial time I saved, to the point where I'm unsure if I'm actually saving much time at the end of the process.

With hobby projects I lean on quality more, and the async nature of AI also makes this much easier to make progress without needing my full attention to do so.

In the corporate world, there's both the pressure to accelerate with AI, but also maintain code and product quality. The dials of one way or the other are more obvious now, but I don't believe it's possible to do both with the current models and harnesses without exponential cost.

What is interesting though, is I'm now leaning towards faster models rather than smarter ones.

Intelligence lets me bite off larger chunks of work at once, and trust the model to behave without having to watch it intensely, but doesn't seem to drive down the number of iterations required to hit my desired quality.

Faster models means the iterations I'll have to go through regardless will complete much faster and gets me closer to a proper flow state. Models will keep improving, but maybe we're getting near "smart enough" and the race will pivot to performance > intelligence.

Cross-platform widget engines (Tk, GTK, Qt, wxWidgets, etc…) long predate Electron and have always been robust, stable, well documented, and easy to use. It's not creating a single application for multiple native desktop environments that was difficult, it's writing a single application as both a web interface and a native desktop environment on any platform that's difficult.

Because CSS is constantly changing, inconsistently implemented, and difficult to use, it can't easily be targeted by widget engines (although Qt has tried, and maybe others) and web browsers already exist, so webview environments like Electron are the quickest way to get a cross-platform installable application that can also be hosted on a web server. I wouldn't really call it native though.

> We built Electron because writing UIs using native desktop frameworks is tough.

No, we built Electron because there are a huge number of people who are too lazy to learn anything outside of HTML/etc for creating a UI. It's not actually hard to make a UI using the native desktop frameworks.

>We built Electron because writing UIs using native desktop frameworks is tough. Is it still tough? Surely LLMs make it easier to use and so we will end up with faster and more native feeling applications.

We built Electron because web devs were a dime a dozen. It was an economic decision, not a technical one.

You would think so. But it seems all that everyone is obsessed with is increasing the velocity of enshitification in the hopes of becoming the next papa Elon

Don’t forget the moment where you realize that instead of cooking a steak the agent went for its own invented requirements and spent all your quota preparing everything to make the perfect ramen from scratch (or at least that’s what it tells you, when you ask it to double check what has been done it comes back and tell you it lied and in fact mixed the flour with the soup without making the noodles, with a small note telling you to not forget to prepare the noodles when you go to production)

Interesting, the NYT had a tip on flipping every 90s, but it was with a cast-iron pan and not a "cold sear". That was too smokey for our weak kitchen exhaust, so it was the last time I tried flipping multiple times.

But Lam Lam's cold sear video doesn't seem to make that much smoke on a non-stick, so I'll give this a shot again.

(Personally the reverse sear has been my idiotproof go-to.)

Thanks!

A software engineer user with taste, yes.

Have you ever been really deep in a thread with an agent on a technical deep dive? The trade-offs conversations would not make sense to someone that is not able to decode the real decisions they’re making.

You can dumb down the agent, but the reason domain language matters is because of the precision of the word sometimes - not to be a gatekeeper.

Anyway - user with taste that understands all the elements of their decisions would be my modifier :)

instead of complaining about what's here, why not go add what you feel is missing?

Soon we will be complaining about wanting just ONE post not related to the mother of all market crashes.

Slight disagree, as many will heat their pan too high and burn the steak before it cooks through. Or maybe that was just me when I first learned how to cook steak the right way. ("Medium"/"medium-high" doesn't necessarily correlate to the position of the knob on the burner or whether the pan feels medium/medium-high)

I was going to say the same thing. 2.5m per side+rotation plus another 2.5 plus or minus 20s depending on heat

But I actually got something out of this -- which is that maybe before now, humans had to soak up the complexity of where value was made in software. And you saw this in the highest and best paid engineers in science and platform teams and basically that you had to invest in brains where you thought the value in your product was.

Without humans managing complexity, you have no idea where you should be investing once the product grows out of the concept stage

Ramen may still be somewhat of a novelty where I live, and I would not call it cheap. Though now that I put that into words, a decent burger anywhere is about the same price..

Pangram says 100% AI, for what it's worth.

I like a good steak but setting off the fire alarms (plural) is a big risk when I cook them in my apartment :-). Scorching hot cast iron pan plus meat means some smoke is unavoidable. And that's the proper way to do it.

The problem with many business leaders is that they don't necessarily understand the businesses they lead very well. That's common for CEOs running a tech company without a tech background. There's a long history of business leaders with MBAs throwing away the baby with the bathwater when they get a bit too enthusiastic cutting cost. It's why Boeing is such a mess. It's why Intel is no longer considered a leader in innovative chips. The likes of Nvidia and Apple are running circles around them. It's why IBM is now a consulting company that hasn't really produced any tech product worth mentioning this century. The only time they are in the news is when they do another layoff round to make share holders happy. They are incapable of innovating because the people that did that have long since left.

In the hands of somebody competent, you can do great things with AI. But if you can't tell good from bad technically, you won't know that you are creating a big stinky mess until it's far too late.

On a positive note, there will be plenty of work for competent techies to come in and straighten things out on a freelance or consultant basis (I'm available for that sort of thing but not cheap). With the help of AI of course. No need to go back to doing things manually. I think a lot of companies will realize they need help in the next years to speed things up, to improve quality, etc. They'll be very opinionated about what they want and used to getting what they want quickly.

It's a level of badly written that makes me think it could be a human, or it might just be an LLM that writes differently from a typical ChatGPT article.

It is slop though, either way.

Why is that a problem?

I love a good medium-rare prime steak, but I also used to live near a restaurant called Best Steak House, which was anything but. However, they delivered a passable steak/steak sandwich that was worth what you paid for it. And considering that they were in business for decades, probably most people felt the same way.

A great steak is an occasional luxury; a "just edible" one is an everyday meal.

That’s what the entire economy does by design. You make the lowest common denominator people will still pay for.

The thesis is covering the flat scenarios mostly. I think the scenario where the job is done so poorly that the steak has to be thrown away needs to be included as well. At times the pans would get damaged. And eventually the business is in debt and needs to be closed

I can go out today and pay $50 for a thick cut ribeye at Ruth's Chris that has been visually inspected for marbling then hard seared in a special high temp over to temp by someone who knows wtf they're doing. I can also go to Denny's and pay $20 for a t-bone cooked to within shouting distance of what I asked for on the same griddle they use for the pancakes that doesn't get the sear I'm looking for.

Point being, you're absolutely right that the goal for a company selling a product is to be barely satisfactory but they don't actually get to decide what's satisfactory.

There is a lot of truth here, but it clearly isn't a welcome one.

From my own perspective I can look back on decades of software I've written (some including code generation far before LLMs), and marvel at the quality and creativity, and lack thereof, from one piece to another.

I never meant to create awful software, but I did (and still sometimes do). With LMM code generation (vs bespoke tooling, T4, XSLT, and the like) the game of chance is part of the fun, harnessing a powerful tool that wants to run out of control on a whim.

Looking back on a couple years of LLM assisted work I see the same mix as the decades before: some great (when I managed to keep the beast restrained) some awful (when I didn't, knowingly or not).

I don't see how things are much different with this tool than others as far as my work product goes. There is a bit more of it, but the excess isn't great stuff (that quantity remains roughly consistent over the years).

I was going to say something similar. In particular, I do a lot of prototyping, AI has allowed me to make prototypes an order of magnitude faster with substantially higher quality. Different types of software engineering have very different goals and standards. AI does cook the perfect medium rare steak every time, but it's able to actually cook steaks in the time it used to take me to like microwave a burrito.

> There's nothing sacred about human-written code

I suspect that there is a lifetime of knowledge and experience wrapped up in that statement and I agree wholeheartedly.

I love writing software and I've been doing it for decades. But I never forget that at the end, there's someone who's paid for it, and needs it to do a job that can't/won't be done manually. And that's why it exists. Not to satisfy my desire to express myself in code, not to allow me to create some golden tower of perfect architecture, but to do a job. Most likely a boring job in the service of increased profitability for some company.

And in the end, the only thing that matters to the customer is if it does that job well enough to be useful. I think -- hell, I know -- that many developers deliberately ignore this critical point.

> All you want is to not be hungry.

This.

Programers are high end chef's whos products are expensive.

LLM / AI tooling is going to do a much better job of delivering on the promise of AppleScript, vb script, IFTT, and every failed drag and drop coding tool that got sold to businesses over the years.

There are going to be gains in large software, from professionals - but the real gains are going to come from all the software that CAN get created that never was before.

There is an XKCD comic "Is It Worth the Time?" (link: https://xkcd.com/1205/ )- a matrix of the cost benefit of automating something. LLM's / AI tooling, generating traditional code, makes the answer "yes" in almost every case now.

I think a certain restaurant chain might have something to say about this