I don't know about VBA, but spreadsheets actually delivered (to a large extent) on the promise that 'everyone can write simple programs'. So much so that people don't see creating a spreadsheet as coding.

Before spreadsheets you had to beg for months for the IT department to pick your request, and then you'd have to wait a quarter or two for them to implement a buggy version of your idea. After spreadsheets, you can hack together a buggy version of your idea yourself over a weekend.

> everyone can code!

I work directly with marketers and even if you give them something like n8n, they find it hard to be precise. Programming teaches you a "precise mindset" that one doesn't have when they aren't really thinking about tech professionally.

I wonder if seasoned UX designers can code now. They do think professionally about software. I wonder if it's at a deep enough granularity such that they can simply use natural language to get something to work.

> It doesn't mean “AI is the new electricity.” (actual quote from Andrew Ng in the post).

I personally agree with Andrew Ng here (and I've literally arrived at the exact same formulation before becoming aware of Ng's words).

I take "new electricity" to mean, it'll touch everything people do, become part of every endeavor in some shape of form. Much like electricity. That doesn't mean taking over literally everything; there's plenty of things we don't use electricity for, because alternatives - usually much older alternatives - are still better.

There's still plenty of internal combustion engines on the ground, in the seas and in the skies, and many of them (mostly on extremely light and extremely heavy ends of the spectrum) are not going to be replaced by electric engines any time soon. Plenty of manufacturing and construction is still done by means of hydraulic and pneumatic power. We also sometimes sidestep electricity for heating purposes by going straight from sunlight to heat. Etc.

But even there, electricity-based technology is present in some form. The engine may be this humongous diesel-burning colossus, built from heat, metal, and a lot of pneumatics, positioned and held in place by hydraulics - but all the sensors on it are electric, where in the past some would be hydraulic and rest wouldn't even exist; it's controlled and operated by electricity-based computing network; it's been designed on computers, and so on.

In this sense, I think "AI is a new electricity" is believable. It's a qualitatively new approach to computing, that's directly or indirectly applicable everywhere, and that people already try to apply to literally everything[0]. And, much like with electricity, time and economics will tell which of those applications make sense, which were dead ends, and which were plain dumb in retrospect.

--

[0] - And they really did try to stuff electricity everywhere back when it was the new hot thing. Same with nuclear energy few decades later. We still laugh at how people 100 years ago imagined the future will look like... in between crying that we got short-changed by reality.

While I'd agree with your first line:

> The problem with LLM is when they're used for creativity or for thinking.

And while I also agree that it's currently closer to "AI is the new VBA" because of the current domain in which consumer AI* is most useful.

Despite that, I'd also aver that being useful in simply "many" contexts will make AI "the new electricity”. Electricity itself is (or recently was) only about 15% of global primary power, about 3 TW out of about 20 TW: https://en.wikipedia.org/wiki/World_energy_supply_and_consum...

Are LLMs 15% of all labour? Not just coding, but overall? No. The economic impact would be directly noticeable if it was that much.

Currently though, I agree. New VBA. Or new smartphone, in that we ~all have and use them, while society as a whole simultaneously cringes a bit at this.

* Narrower AI such as AlphaFold etc. would, in this analogy, be more like a Steam Age factory which had a massive custom steam engine in the middle distributing motive power to the equipment directly: it's fine at what it does, but you have to make it specifically for your goal and can't easily adapt it for something else later.

LLM is helpful for creativity and thinking When you run out of your ideas

100%. AGI is some arbitrary threshold that has nothing to do with LLMs and their broad application, rapid improvement and exploding ecosystem. The only comparable shift in memory is the advent of the Internet, and that was much slower for obvious reasons (everyone needs a computer, needs to use the phone line, needs to upgrade to faster internet, etc., etc.)

LLMs are just here and accessible to everyone with all kinds of uses. And people that hate them and don't want LLMs shoved in their face: it doesn't matter. Chatbots were already a thing for customer service, now they are almost implicit. SaaS in general is going to be completely revamped. Huge companies are going to have a shift like they did when they first digitized paper files. This is seismic and a large-scale structural upgrade to many institutions.

And that is without giving a shit about public facing LLMs or Ghibli art or writing your term papers for you. It doesn't have anything to do with AI making you dumb or being shoved into products. That is random noise, big picture. Anyone that can't see the real changes to business and knowledge retrieval isn't thinking this through or is actively burying their heads in the sand.

I doubt that LLM will keep getting better, too. Or at least, not in an economically sustainable way

Yes, people often conflate the two. ChatGPT is nice for some coding things and asking what you want for dinner. That does not mean we're all out of a job and our society has to be radically rethought.

Regarding your plane story, I can't help but notice that the fact this plane was in operation, and they were willing to fly on it, implies the problem wasn't that big of an issue.

Are you sure code from another developer (junior or not) works correctly? Or that it is secure? You have the same need to review the code regardless of the source.

This is how non-engineers have always lived! The code is a black box, but Product Managers develop a sense of whether the developer really understood what they meant, the QA team verifies the outputs, etc.

I'm uncertain if MY code works correctly lol. I know many code-illiterate folk; some of them I call "boss" or "client." They get along fine dining on my spaghetti. I do likewise never touching the wheel/pedals on my car's 45-minute commute to work.

Will someone eventually be scraping me off of the highway? Will my bosses stop printing money with my code? Possibly! But that's life -- our world is built upon trust, not correctness.

Absolutely couldn’t agree more. Incredibly useful tools are, in fact, incredibly useful. These discussions get clouded though when we intentionally ignore what’s being said by those doing the investing. The inevitability here isn’t that they’ll save 30% of dev time and we’ll get better software with less employees. It’s that come 2030, hell there’s that 2027 paper even, LLMs will be more effective than people at most tasks. Maybe at some point that’ll happen but looking at other normal technology[0] it takes decades.

0: https://knightcolumbia.org/content/ai-as-normal-technology

> where a program writes arbitrary programs for us

That seems like a strange requirement and I am not sure where you are getting it from. Programs are not arbitrary, and software design is something you will need to do at some level; you need to at least be able to describe the problem you are having and getting that right has been the hardest part of software development for a long time.

Just try to imagine what you would have thought about this technology if you saw it with no warning, 10 years ago. Would "a few tens of thousands of lines of code" still seem small?

They are not wrong.

The market, meant in a general sense, is stronger than any individual or groups of people. LLMs are here, and already demonstrate enough productive value to make them in high demand for objective reasons (vs. just as a speculation vehicle). They're not going away, nor is larger GenAI. It would take a collapse of technological civilization to turn the tide back now.

I have a parallel to suggest; I know it's the rhetorical tool of analogous reasoning, but it deeply matches the psychology of the way most people think. Just like getting to a "certain" number of activated parameters in a model (for some "simple" tasks like summarisation) can be as low as 1.8 billion, once that threshold is breached the "emergent" behaviour of "reasonable", "contextual", or "lucid" text is achieved; or to put this in layman's terms, once your model is "large enough" (and this is quite small compared to the largest models currently in daily use by millions) the generated text goes from jibberish to uncanny valley to lucid text quite quickly.

In the same way once a certain threshold is reached in the utility of AI (in a similar vein to the "once I saw the Internet for the first time I knew I would just keep using it") it becomes "inevitable"; it becomes a cheaper option than "the way we've always done it", a better option, or some combination of the two.

So, as is very common in technological innovation / revolution, the question isn't will it change the way things are done so much as where will it shift the cost curve? How deeply will it displace "the way we've always done it"? How many hand weaved shirts do you own? Joseph-Marie Jacquard wants to know (and King Cnut has metaphorical clogs to sell to the Luddites).

There is an old cliché about stopping the tide coming in. I mean, yeah you can get out there and participate in trying to stop it.

This isn't about fatalism or even pessimism. The tide coming in isn't good or bad. It's more like the refrain from Game of Thrones: Winter is coming. You prepare for it. Your time might be better served finding shelter and warm clothing rather than engaging in a futile attempt to prevent it.

The year is 1985. Internet is coming. You don't want it to.

Can you stop it?

Isn't it kind of both?

Did luddites ever have a chance of stopping the industrial revolution?

You can fight against the current of society or you can swim in the direction it's pulling you. If you want to fight against it, you can, but you shouldn't expect others to. For some, they can see that it's inevitable because the strength of the movement is greater than the resistance.

It's fair enough to say "you can change the future", but sometimes you can't. You don't have the resources, and often, the will.

The internet was the future, we saw it, some didn't. Cryptocurrencies are the future, some see it, some don't. And using AI is the future too.

Are LLMs the endpoint? Obviously not. But they'll keep getting better, marginally, until there's a breakthrough, or a change, and they'll advance further.

But they won't be going away.

The reality for most people is that at a macro level the future is something that happens to them. They try to participate e.g. through voting, but see no change even on issues a significant majority of 'voters' agree on, regardless of who 'wins' the elections.

The day I can put on a pair of AR glasses as lightweight as my current glasses and gain better vision, I'd pay a huge amount for that.

I hate my varifocals because of how constrained they make my vision feel...

And my vision is good enough that the only thing I struggle with without glasses is reading.

To me, that'd be a no-brainer killer app where all of the extra AR possibilities would be just icing.

Once you get something like enough and high resolution enough, you open up entirely different types of applications like that which will widen the appeal massively, and I think that is what will then sell other AR/VR capability. I'm not interested enough to buy AR glasses for the sake of AR alone, but if I could ditch my regular glasses (without looking like an idiot), then I'm pretty sure I'd gradually explore what other possibilities it'd add.

Every single HN post on AI or crypto I see this argument and it’s exhausting.

When Eliza was first built it was seen a toy. It took many more decades for LLMs to appear.

My favourite example is prime numbers: a bunch of ancient nerds messing around with numbers that today, thousands of years later, allow us to securely buy anything and everything without leaving our homes or opening our mouths.

You can’t dismiss a technology or discovery just because it’s not useful on an arbitrary timescale. You can dismiss it for other reasons, just not this reason.

Blockchain and related technologies have advanced the state of the art in various areas of computer science and mathematics research (zero knowledge proofs, consensus, smart contracts, etc.). To allege this work will bear no fruit is quite a claim.

> With the “metaverse”, you clear out a space around you, strap a heavy thing on your head, and shut yourself into an artificial environment. After the first oohs and aahs, you enter a VR chat room… And realize the thing on your head adds absolutely nothing to the interaction.

It doesn't if you use it as just a chat room. For some people it does add a lot, though.

The "metaverse" as in Active Worlds, Second Life, VR Chat, our own Overte, etc has been around for a long time and does have an user base that likes using it.

What I'm not too sure about is it having mass appeal, at least just yet. To me it's a bit of a specialized area, like chess. It's of great interest to some and very little to most of the population. That doesn't mean there's anything wrong with places like chess.com existing.

I think AI is inevitable in the way that bitcoin is now inevitable: it's not going to go away, it consumes a huge amount of energy, has various negative externalities, but a massive fanbase.

It doesn't really matter whether crypto is "useful", it has billions of dollars worth of fans. Similarly the LLM fans are not going to go away. However, there will probably be curated little oases for human-made works. We're also going to see a technique adapted from self-crashing cars: the liability human. A giant codebase is launched and a single human "takes responsibility" (whatever that ends up meaning) for the failures.

> With crypto, it’s still the case that you create a wallet and then… there’s nothing to do on the platform. You’re expected to send real money to someone so they’ll give you some of the funny money that lets you play the game.

This became a problem later due to governments cracking down on cryptos and some terrible technical choices made transactions expensive just as adoption was ramping. (Pat yourselves on the back, small blockers.)

My first experience with crypto was buying $5 in bitcoin from a friend. If I didn't do it that way I could go on a number of websites and buy crypto without opening an account, via credit card, or via SMS. Today, most of the $5 would be eaten by fees, and buying for cash from an institution requires slow and intrusive KYC.

> And realize the thing on your head adds absolutely nothing to the interaction.

There are some nice effects - simulating sword fighting, shooting, etc.

It's just benefits still outweigh the cost. Getting to "good enough" for most people is just not possible in short and midterm.

Bitcoin seems to be working as a kind of digital gold if you look at price development. It's not that much about technology though.

Give it some time - just like LLMs the first VR headsets were created in the 90s (for example by Nintendo). But it took another 30 years for the hardware to achieve levels of functionality and comfortableness that make it a viable consumer product. Apple Vision is starting to get there. And crypto is even younger - it started in early 2009. For people living in countries without a proper banking infrastructure the stablecoins are already very helpful. Billions of people live in countries that don't have a well audited financial sector, that respects the rule of law or an independent central bank that makes sound monetary decisions irrespective of the government. For them stablecoins and their cheap transactions are huge.

The question I have for your observation (which I think is correct btw) is:

Do you think it's inherent to the technology that the use cases are not useful or is it our lack of imagination so far that we haven't come up with something useful yet?

I feel like my personal experience of the metaverse is a really good comparator for LLM’s. Really cool, I can see the possibilities, I want it! It seems like it’s there, But I can also see that the gap between what exists and what would make it truly useful is too great.

How much of the code you are writing is tedious? If its a significant amount, the framework you are using could use some improvement.

Funny you use something the author of the linked post talks about at the start. This is one of those debate methods. Reframe what was said!

I don't remember that the OP claimed that all problems are solved, perfectly. Do you think by showing examples where AI struggles you really show their point to be wrong? I don't see that.

I use AI only sparingly, but when I do I too experience saving lots of time. For example, I'm only superficially familiar with MS Excel or Power Query scripting APIs and function names. Too bad I've become the got-to point for little mean problems for colleagues. Instead of having to read lots of docs and do lots of trial and error, I now formulate what I want to ChatGPT, give it the file, and thus far I have always received the solution, a transformed file. Sure, anyone regularly using Excel/Power Query could have written the few lines of code easily enough, but since I don't, and don't plan to, being able to use plain language and let the AI do the actual coding is a huge time saver.

For SOME problems in this world it works. Nobody claimed anything you seem to be trying to argue against, that it solves ALL problems, so that finding one or a few counter-examples where it fails invalidates the argument made. And the problems it does solve are not trivial and that it works is quite miraculous and was not possible before.

Did you build the house you live in? Did you weave your own clothes or grow your own food?

We all depend on systems others built. Determining when that trade-off is worthwhile and recognizing when convenience turns into dependence are crucial.

> and you learned nothing in the process.

why do you presume the person wanted to learn something, rather than to get the work done asap? May be they're not interested in learning, or may be they have something more important to do, and saving this time is a life saver?

> You are losing autonomy and depending more and more on external companies

do you also autonomously produce your own clean water, electricity, gas and food? Or do you rely on external companies to provision all of those things?

> Hours of time saved, and you learned nothing in the process

Point and click "engineer" 2.0

We all know this.

Eventually someone has to fix the mess and it won't be him. He will be management by then.

these 3090s are mine. hands off!

For the internet to be democratizing it needed PCs first. Before that computing was like LLMs: the mainframe era. You either had access to an institution with a mainframe or you were luckily able to get a thin client to a mainframe (the early time-sharing systems.) Even after PCs were invented, for decades mainframes were inarguably better than PCs. Mainframes and thin clients were even some of the earliest computer networks.

I am optimistic that local models will catch up and hit the same pareto-optimal point. At some point your OS will ship with a local model, your system will have access to some Intelligence APIs, and that's that. Linux and BSDs will probably ship with an open-weights model. I may be wrong, but this is my hope.

If you're interested in a taste of that future try the Gemma3 class of models. While I haven't tried agentic coding with them yet, I find them more than good enough for day-to-day use.

> Many of us remember the rise of the world wide web, and perhaps even personal computing that made the internet mainstream.

I do. The web was the largest and most widespread enshittification process to date, and it started with the first sale made online, with the first ad shown on a web page - this quickly went into full-blown land grab in the late 90s, and then dotcom and smartphones and social media and SaaS and IoT and here we are today.

The "propensity for enshittification" is just called business, or entrepreneurship. It is orthogonal to AI.

I think comparing rise of LLMs to the web taking off is quite accurate, both with the good and bad sides.

There is a skill to it. You can get lucky as a beginner but if you want consistent success you gotta learn the ropes (strengths, weaknesses, failure modes etc).

A quick way of getting seriously improved results though: if you are literally using GPT-4 as you mention—that is an ancient model! Parent comment says GPT-4.1 (yes openai is unimaginably horrible at naming but that ".1" isn't a minor version increment). And even though 4.1 is far better, I would never use it for real work. Use the strongest models; if you want to stick with openai use o3 (it's now super cheapt too). Gemini 2.5 Pro is roughly equivalent to o3 for another option. IMO Claude models are stronger in agentic setting, but won't match o3 or gemini 2.5 pro for deep problem solving or nice, "thought out" code.

LLM apology cascade:

- That didn’t happen.

- And if it did, I’m really sorry.

- And if it was that bad, I truly apologise.

- And if it is a big deal, I understand and I’m sorry again.

- And if it’s my fault, I’ll try to do better.

- And if I meant it… I didn’t — but I’m still sorry.

Yes, arguing with an LLM in this way is a waste of time. It’s not a person. If it does anything weird, start a new conversation.

Totally agree, had same experience couple of times, and until now no experience like that of the OP.

BUT: in the 90s I remember saying: supposedly in internet is all and everything, but I never find what I need, is more ads than actual information.

So the I think the point of OP holds. It may (today) not be useful for you, but maybe in some years, and if not, will still ve useful for many people, and is here to stay.

> "I didn’t actually execute Python scripts ... my “test” was a mental simulation based on my knowledge"

Pretty sure the part of the training corpus that produced that was written by an ex cow orker of mine...

I perceive a huge divide between people that (try to) use dialog systems (e.g. ChatGPT, CoPilot) for programming and people that use (and pay for) dedicated programming agents (Cursor, Clint, etc).

From my experience using both, only the later is worth using.

Did you ever think there's a reason why people are paying for professional tools like Cursor or Claude Code instead of using free ChatGPT?

Ye, the free version has some known issues. They cram a lot of stuff into GPT-4o, so it hallucinates a lot.

Claude Opus 4 often gives perfectly working code on the first try, and it's much less likely to hallucinate or argue with you when it's wrong. It costs around $1 per request though. Not cheap. It's a model with many trillions of weights and running it isn't cheap.

So did it actually give you a config file? And did it work or fail?

If it didn't give you a config file I really don't understand why your followup wasn't getting it to spit one out, and instead you decided to ask it questions about an obviously fake laptop.

In a code editor or the website? Coding using the website has distinct disadvantages, imo.

But yeah… Arguing with an LLM is never worthwhile. If it doesn’t (mostly) work the first time, roll back and start over with a better prompt. This is because there is a big element of randomness (seed) that causes every run to potentially be different, ranging from slight to drastic. Basically, you can get junior dev who should be fired one time, and a senior engineer the next. Start over, improve the prompt/context/plan, run it again. E.g. there is a reason the Copilot in-line editor has that little try again button right there; because you should use it, same with entire prompts—hence the reason the up arrow in VS Code Copilot gives you back your last prompt.

Also, lots of times it means it just doesn’t have the right context to pull from (or too much, or not useful, depending on the model). Small well-defined tasks are almost always better. Documentation in an LLM readable/searchable format can be highly beneficial, especially API references for libraries that are well organized, or things like Context7 MCP if the library is recent or can be parsed correctly by C7. Expecting a general knowledge LLM to be an expert in every language/library or to just intuit correctly from the library sources hasn’t ever worked out well in my experience (unless it is a small library).

At least that’s my 2 cents if you’re interested. Hope it is helpful (to someone).

Today I learned that ChatGPT is akin to Seymour Skinner when pressed about the truth of its steamed hams recipe.

Why were you so hung up on whether it had a laptop or not? You know that it doesn't, don't you?

Get it to write the code, then you test it.

This is the future, this is inevitable.

(Sorry, couldn't resist)

This is shit, and there's no way this kind of shit is passing the Turing test.

Many people were extremely skeptical of the internet in the early 90s. You can find old clips of news shows basically mocking the idea.

They also destroyed our cities, and are one of the major contributors to the destruction of the climate to which we are adapted.

> You've gotta augment that with a good testing strategy.

It's OK. The LLM will also write those and all will be good.

You'll be lucky if it even compiles, but who cares?

Here is mine: I had never used pydantic before, but I know TS very well. "Here is a Typescript type, explain how it would be expressed in Pydantic and the differences in what each type system is able to express."

Boom, instant education on Pydantic through the lens of a language I understand very well.

Computers ruined entry level jobs for a lot of people. Heck Outlook and PowerPoint put a lot of people out of work. Personal secretary used to be a solid reliable job for many women. Art teams used to exist to make real life presentations on actual paper. Large companies had their own private libraries and librarians to fetch documents.

Arguably we already saw some of the socially destabilizing impacts of computers, and more and more Americans were forced into poorly paying service sector jobs.

I actually suspect that right now, if we wanted to, we could automate a large amount of societies needs if we were willing to take a hit on quality/variety. For example, what % of the food chain could be 100% automated if we really wanted to? Obviously most foods could not, but surely a few staple crops could be automated 100% to the extent of robo-semis and robots loading and unloading crops?

That will be the eventual end goal. The question is what do we do as a society then?

i would disagree we kind of figured it out early. Early visions for internet were about things like information superhighway (with a centralized approach). What came to pass was the opposite. Its a good thing. There are lessons here in that we are not always accurate at predicting what the future would look like. But we can always identify trends that may shape the future.

Can you translate "SFT'd" and "TTFT" and "TESCREAL" for the less clued-in members of the audience? On "one ine itabalism" I just gave up.

This comment is absolute bullshit.

It starts off being wrong ("Opus 4 has maxed out LLM coding performance"), then keeps being wrong ("LLM inference is sold at a loss"), and tries to mask just how wrong it at any point in time is by pivoting from one flavor of bullshit to another on a dime, running laps a manic headless chicken.

A lot of people are missing this point. It's not about what it can do today. It's about what all you're promised it can do and then be sold to you like there's no alternative; and no one really knows if it will be able to do it or what all non-KPI functions are lost because AI is the only way ahead.

Having used a customer service, I just happen to know that a smarter and a better chat-bot for a bog-standard service request (like a road-side car breakdown) isn't the solution for a better experience.

But now, since a chat bot is cheaper to run, the discussion in the service provider HQ will be about which chat-bot technology to migrate to because user research says it provides for an overall better UX. No one remembers what it is to talk to a human.

All of those studies have been torn apart in detail, often right here on HN.

> So while it may be a fun toy for senior devs that know what to look for, it actually makes them slower and stupider, making them progressively less capable to do their job and apply critical thinking skills.

I've been able to tackle problems that I literally would not have been able to undertake w/o LLMs. LLMs are great at wading through SO posts and GH issue threads and figuring out what magic set of incantations makes some stupid library actually function. They are really good at writing mock classes way faster than I ever have been able to. There is a cost/benefit analysis for undertaking new projects, and if "minor win" involves days of wading through garbage, odds are the work isn't going to happen. But with LLMs I can outsource the drudgery part of the job (throwing crap tons of different parameters at a poorly documented function and seeing what happens), and actually do the part that is valuable (designing software).

You still have to guide the design! Anyone letting LLMs design software is going to fail hard, LLMs still write some wacky stuff. And they are going to destroy juniors, I don't know what the future of the field is going to be like (not pretty that is for sure...)

But I just had an LLM write me a script in ~2 minutes (me describing the problem) that would've taken me 30-60 minutes to write and debug. There would have been no "learning" going on writing a DOS batch script (something I have to do once very 2 or 3 years, so I forget everything I know each time).

These studies profoundly miss the mark and were clearly written for engagement/to push a certain view. It's abundantly clear to any developer who has used LLMs that they are a useful tool and have turned the corner in terms of the value they're able to provide vs their limitations.