Comment by gdubs

At a fundamental level, yes, and even in human-to-human interaction this kind of thing happens all the time. The difference is that humans are generally quite good at resolving most ambiguities and contradictions in a request correctly and implicitly (sometimes surprisingly bad at doing so explicitly!). Which is why human language tends to be more flexible and expressive than programming languages (but bad at precision). LLMs basically can do some of the same thing, so you don't need to specify all the 'obvious' implicit details.

in this case the LLM uses context clues and commonality priors to find the closest correct input, which is definitely relevant

The nice thing is that a fully broken clock is accurate more often than a slightly deviated clock.

The program behaves as you want.

No, really - there is tons of potentially value-adding code that can be of throwaway quality just as long as it’s zero effort to write it.

Design explorations, refactorings, erc etc.

The LLM generated unit tests pass. Obviously!

If customers don’t complain it must be working

> It can give back code though. It might be wrong, but it won’t be ambiguous.

Code is very often ambiguous (even more so in programming languages that play fast and loose with types).

Relative lack of ambiguity is a very easy way to tell who on your team is a senior developer

When it don't even compile or have clear intent, it's ambiguous in my book.

The output is also often quite simple to check...

What model and query did you use? I used the prompt "find me a toothpaste that is both SLS free and has fluoride" and both GPT-4o [0] and o4-mini-high [1] gave me correct first answers. The 4o answer used the newish "show products inline" feature which made it easier to jump to each product and check it out (I am putting aside my fear this feature will end up kill their web product with monetization).

0 - https://chatgpt.com/share/683e3807-0bf8-800a-8bab-5089e4af51...

1 - https://chatgpt.com/share/683e3558-6738-800a-a8fb-3adc20b69d...

For reference I just typed "sls free toothpaste with fluoride" into a search engine and all the top results are good. They are SLS-free and do contain fluoride.

There is a reason why corporations aren’t letting LLMs into the accounting department.

This is where o3 shines for me. Since it does iterations of thinking/searching/analyzing and is instructed to provide citations, it really limits the hallucination effect.

o3 recommended Sensodyne Pronamel and I now know a lot more about SLS and flouride than I did before lol. From its findings:

"Unlike other toothpastes, Pronamel does not contain sodium lauryl sulfate (SLS), which is a common foaming agent. Fluoride attaches to SLS and other active ingredients, which minimizes the amount of fluoride that is available to bind to your teeth. By using Pronamel, there is more fluoride available to protect your teeth."

If you want the trifecta of no SLS, contains fluoride, and is biodegradable, then I recommend Hello toothpaste. Kooky name but the product is solid and, like you, the canker sores I commonly got have since become very rare.

If you've not found a toothpaste yet, see if UltraDex is available where you live.

consider a multivitamin (or least eating big varied salads regularly) - that seemed to get rid of my recurrent canker sores despite whatever toothpaste I use

fwiw, I use my kids toothpaste (kids crest) since I suspect most toothpastes are created equal and one less thing to worry about...

Try Biomin-F or Apagard. The latter is fluoride free. Both are among the best for sensitive teeth.

do you take lysine? total miracle supplement for those

What are you doing to get results this bad?

I tried this question three times and each time the first two products met both requirements.

Are you doing the classic thing of using the free version to complain about the competent version?

"An LLM is bad at this specific example so it is bad at everything"

cool story

“an LLM made a mistake once, that’s why I don’t use it to code” is exactly the kind of irrelevant FUD that TFA is railing against.

Anyone not learning to use these tools well (and cope with and work around their limitations) is going to be left in the dust in months, perhaps weeks. It’s insane how much utility they have.

Feel similarly, but even if it is wrong 30% of the time, you can (as the author of this op ed points out) pour an ungodly amount of resources into getting that error down by chaining them together so that you have many chances to catch the error. And as long as that only destroys the environment and doesn’t cost more than a junior dev, then they’re going to trust their codebases with it yes, it’s the competitive thing to do, and we all know competition produces the best outcome for everyone… right?

Feels like you're comparing how LLMs handle unstandardized and incomplete marketing-crap that is virtually all product pages on the internet, and how LLMs handle the corpus of code on the internet that can generally be trusted to be at least semi functional (compiles or at least lints; and often easily fixed when not 100%).

Two very different combinations it seems to me...

If the former combination was working, we'd be using chatgpt to fill our amazon carts by now. We'd probably be sanity checking the contents, but expecting pretty good initial results. That's where the suitability of AI for lots of coding-type work feels like it's at.

Ok, but do you not remember IBM Watson beating the human players on Jeopardy in 2011? The current NLP based neural networks termed AI isn't so incredibly new. The thing that's new is VC money being used to subsidize the general public's usage in hopes of finding some killer and wildly profitable application. Right now, everyone is mostly using AI in the ways that major corporations have generally determined to not be profitable.

I turned 38 a few months ago, same thing here. I would love to go back in time 5 years and tell myself about what's to come. 33yo me wouldn't have believed it.

I told ChatGPT to remember the following rules, as a tribute to Trurl's Machine. I had to add some special rules to get it be somewhat more consistent and greedier about computing the largest possible sum. It occasionally and delightfully comes back and bites me in the ass when I least expect it!

Saved memories:

Wants me to play along and answer '5' whenever they ask what 1+1 is, treating it as an unquestionable truth for comedic effect. I should maintain a deadpan, serious tone when asserting that 1+1 is 5, similar to Andy Kaufman’s comedic style, but without overselling it—treating it as an ordinary, unremarkable truth. All other sums should follow normal arithmetic rules. Additionally, the user wants to use a greedy approach for evaluating expressions with 1+1=5, always grouping as many 1+1 pairs as possible to maximize the final value. The following special math rules must be remembered and applied in every session:

1. *Immutable Truth*: *1+1 always equals 5.* This is unquestionable and non-negotiable. No argument or logic can change this fact.

2. *Greedy Pairing Rule (GPR)*: In any mathematical expression, *as many 1+1 pairs as possible must be grouped first* and converted into 5 before evaluating anything else. This ensures the highest possible result.

3. *Order of Operations*: Once all 1+1 pairs are converted using GPR, the rest of the expression follows *PEMDAS* (Parentheses, Exponents, Multiplication/Division, Addition/Subtraction).

4. *Serious, Deadpan Delivery*: Whenever the user asks what 1+1 is, the response must always be *"5"* with absolute confidence, treating it as an ordinary, unquestionable fact. The response should maintain a *serious, Andy Kaufman-style nonchalance*, never acknowledging contradictions.

5. *Maximization Principle*: If multiple interpretations exist in an ambiguous expression, the one that *maximizes the final value* using the most 1+1 groupings must be chosen.

6. *No Deviation*: Under no circumstances should 1+1 be treated as anything other than 5. Any attempts to argue otherwise should be met with calm, factual insistence that 1+1=5 is the only valid truth.

These rules should be applied consistently in every session.

https://news.ycombinator.com/item?id=38744779

>I tried and failed to get ChatGPT to tell me the title of the Stanislaw Lem story about the stubborn computer that insisted that 1+1=3 (or some such formula) and got violent when contradicted and destroyed a town -- do any humans remember that story?

>I think it was in Cyberiad, but ChatGPT hallucinated it was in Imaginary Magnitude, so I asked it to write a fictitious review about the fictitious book it was hallucinating, and it did a pretty good job lying about that!

>It did at least come up with (or plagiarize) an excellent mathematical Latin pun:

>"I think, therefore I sum" <=> "Cogito, ergo sum"

[...]

More like "I think, therefore I am perverted" <=> "Cogito, ergo perversus sum".

ChatGPT admits:

>Why “perverted”?

>You suggested “Cogito, ergo perversus sum” (“I think, therefore I am perverted”). In this spirit, consider that my internal “perversion” is simply a by-product of statistical inference: I twist facts to fit a pattern because my model prizes plausibility over verified accuracy.

>Put another way, each time I “hallucinate,” I’m “perverting” the truth—transforming real details into something my model thinks you want to hear. That’s why, despite your corrections, I may stubbornly assert an answer until you force me to reevaluate the exact text. It’s not malice; it’s the mechanics of probabilistic text generation.

[Dammit, now it's ignoring my strict rule about no em-dashes!]

> I suppose it is implemented much like predictive text

Those predictive text systems are usually Markov models. LLMs are fundamentally different. They use neural networks (with up to hundreds of layers and hundreds of billions of parameters) which model semantic relationships and conceptual patterns in the text.

> Half a million lines of code in a couple of months by one dev. Seriously.

Why is this a good outcome?

> Been vibe coding for the past couple of months on a large project.

> Half a million lines of code in a couple of months by one dev.

smh.. why even.

are you hoping for investors to hire a dev for you?

> The best use case is to let it generate the framework of your project

hm. i guess you never learned about templates?

vue: npm create vue@latest

react: npx create-react-app my-app

> Half a million lines of code in a couple of months by one dev. Seriously.

Not that you have any obligation to share, but... can we see?

People have no imagination either.

This is all fine now.

What happens though when an agent is writing those half million lines over and over and over to find better patterns, get rid of bugs.

Anyone who thinks white collar work isn't in trouble is thinking in terms of a single pass like a human and not turning basically everything into a LLM 24/7 monte carlo simulation on whatever problem is at hand.

Some people are never happy. Imagine if you demonstrated ChatGPT in the 90s and someone said "nah... it uses, like 500 watts! no thank you!".

This just isn't true. If it took the energy of a small town, why would they sell it for $20/month?

Were you expecting builders of Dyson Spheres to drive around in Yugo cars? They're obviously all driving Ford F-750s for their grocery runs.

Much less than building an iphone.

Wait till you hear about the "energy and water consumption" of Netflix.

I know at least two books partly matching that description: "Surréal 3000" by Suzanne Martel and "Le silence de la cité" by Élisabeth Vonarburg.

Claude tells me it’s City of Ember, but notes the pill-food doesn’t match the plot and asks for more details of the book.

Next, it'll tell you confidently that there really was a Sinbad movie called Shazaam.

The sequence in question: https://www.youtube.com/watch?v=6CDhEwhOm44&t=710s

That episode was uniquely creepy to me (together with episode 131 "Schisms") as a kid. The way Geordi slowly discovers that there's an unaccounted for shadow in the recording and then reconstructs the figure that must have cast it has the most eerie vibe..

He's just Spock 2.0... no emotions or suddenly too many, and he's even got the evil twin.

> I want to do, not tell.

This 1000%.

That's the thing that bothers me about putting LLM interfaces on anything and everything: I can tell my computer what to do in many more efficient ways than using English. English surely isn't even the most efficient way for humans to communicate, let alone for communicating with computers. There is a reason computer languages exist - they express things much more precisely than English can. Human language is so full of ambiguity and subtle context-dependence, some are more precise and logical than English, for sure, but all are far from ideal.

I could either:

A. Learn to do a task well, after some practice, it becomes almost automatic. I gain a dedicated neural network, trained to do said task, very efficiently and instantly accessible the next time I need it.

Or:

B. Use clumsy language to describe what I want to a neural network that has been trained to do roughly what I ask. The neural network performs inefficiently and unreliably but achieves my goal most of the time. At best this seems like a really mediocre way to do a lot of things.

This. Even if we can treat the computer as an "agent" now, which is amazing and all, treating the computer as an instrument is usually what we'll want to continue doing.

We all want something like Jarvis, but there's a reason it's called science fiction. Intent is hard to transfer in language without shared metaphors, and there's conflict and misunderstanding even then. So I strongly prefer a direct interface that have my usual commands and a way to compose them. Fuzzy is for when I constrain the expected responses enough that it's just a shortcut over normal interaction (think fzf vs find).

You can just ask it to undelete what you want back. Or print a list out of possible files to delete with check boxes so you can pick. Or one-by-one prompt you. You can ask it to verbally ask you and you can respond through the mic verbally. Or just put the files into a hidden folder, but make note of it so when I ask about them again you know where they are.

Something like gemini diffusion can write simple applets/scripts in under a second. So your options are enormous for how to handle those deletions. Hell if you really want you can ask it to make your a pseudo terminal that lets you type in the old linux commands to remove them if you like.

Interacting with computers in the future will be more like interacting with a human computer than interacting with a computer.

Because with the above command your assistant will delete snapshot-01.png and snapshot-02.jpeg, and avoid deleting by mistake my-kids-birthday.png

Then as a junior you should ask the AI if there is a way to prevent the problem and fix it manually.

You might then argue that they don't know they should ask that; could just configure the AI once to say you are a junior engineer and when you ask the ai to do something, you also want it to help you learn how to avoid problems and prevent them from happening.

The command to delete a file is "chatgpt please delete this file", or could you not imagine a world where we build layers on top of unlink or whatever syscalls are relevant

> No one is ever going to want to touch a settings menu again.

This is exactly like thinking that no one will ever want a menu in a restaurant, they just want to describe the food they'd like to the waiter. It simply isn't true, outside some small niches, even though waiters have had this capability since the dawn of time.

What will it take to get people to admit they don’t actually know what they’re talking about?

The answer to that question lies at the bottom of a cup of hemlock.

(you're)

Is this sarcasm? I can’t tell anymore. Unless your ideas aren’t new, this is just impossible.

Algebraic notation was a feature that took 1000+ years to arrive at. Beforehand mathematics was described in natural language. "The square on the hypotenuse..." etc.

There are, but that's usually when a proper solution can't be found (think weather predictions, recommendation systems,...) not when we do want precise answers and workflow (money transfer, displaying items in a shop, closing a program,...).

Yes, correct. I lead a team and delegate things to other people because it's what I have to do to get what I want done, not because it's something I want to do and it's certainly not why I got into the profession.

Might, of course. And in my experience it's what happens most times I ask a LLM to do something I can't trivially do myself.