Almost no skill required to cook a steak

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

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.

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.

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.

Perfect grilled steak, especially well-done, is something I find very few people have the experience or skills to do well, especially over a coal grill where the heat won't be constant and the person also need to first have good experience in making a good and even coal bed.

Imagine someone walking into their local grocer, grabbing a prepackaged porterhouse steak (because it's fancy right?), salt and pepper (because for a good steak that's all you need, right) and then wondering why part of it tastes bland and overdone, and the other part bland and under-done.

Sounds pretty analogous imo.

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".

A meat probe and the 30-second flip technique is a stupid-easy way to a perfect steak every time. Just make sure you've got great ventilation. Also salt the meat 1 hour before.

Some people just want to _cook the steak_.

They don't want to attend or understand to cuts, thermometers, and searing.

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.

is it rare, medium-rare, medium, well-done?

i think it is subjective.

It’s not surprising people on HN find it easy because attention to detail is rewarded in this community/its employers. But common here and common are different beasts.

I'll leave it to you to figure out how to unfuck AI, but I reckon 600 watts won't provide enough inference capacity.

> 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?

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

It’s great to yearn for bug free software, but that necessarily brings an insane amount of red tape to get anything done. Like 5 years worth of review to start building your code with the next version of your compiler. Or six months to ship a hundred lines of code.

I'd rather have bugs. I’d happily quit having anything to do with software than suffer months of doing nothing in the name of security.

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

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

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.

Those existing make the comparison a bit silly. Though, given how those seem to be somewhat of a niche that few people know or care about maybe automated perfection isn't what all people have an interest in. Process vs. result and all that. Or maybe it's just that few people realize that optigrills are a thing that exist and how good they are.

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.

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.

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

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!

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 :)

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 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.

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.

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

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 is slop though, either way.

(with apologies to Mike from The Young Ones)

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.

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.