[pico303]

I’m a dev working with AI to build tools for others, but I don’t use them personally. Why? Because they make your writing sound like everyone else, they produce shoddy and broken code (unless you’re doing something really commonplace), and they dull your own creativity. If you’re relying on someone else to do your work, you’re going to lose the ability to think for yourself.

AI is built essentially on averages. It’s the summary of the most common approach to everything. All the art, writing, podcasts, and code look the same. Is that the bland, unimaginative world we’re looking for?

I love the bit in the study about the “fear” of AI. I’m not “afraid” it’ll produce bad code. I know it will; I’ve seen it do it 100 times. AI is fine as one tool to help you learn and think about things, but don’t use it as a replacement for thinking and learning in the first place.

[ofjcihen]

I need to second all of these points and add in the additional reason I don’t use it often: unless it’s a very common use case and I just need some boilerplate starting code I already know I’m going to spend more time fixing the issues it creates than if I just write it myself.

[standardUser]

> they produce shoddy and broken code

We must have dramatically different approaches to writing code with LLMs. I would never implement AI-written code that I can't understand or prove works immediately. Are people letting LLMs write entire controllers or modules and then just crossing their fingers?

[stackskipton]

Yes. VAST majority of developers are working in feature factories where they pick a Jira ticket off the top, it probably has timeboxed work amount. Their goal is close Jira ticket within timeboxed amount by getting build to go green and PM to accept "Yep, that feature was implemented." If badly written LLMs will get build to go green and feature to be accepted, whatever, Jira ticket closed, paycheck collected. Any downstream problems are tomorrow problem when tech debt piles up high enough and Jira tickets to fix the tech debt are written.

[sotix]

> > they produce shoddy and broken code

> We must have dramatically different approaches to writing code with LLMs.

I’ve seen this same conversation occur on HN every day for the past year and a half. Help! I think I’m stuck in an llm conversation where it keeps repeating itself and is unable to move onto the next point.

[ofjcihen]

In my experience: Yes.

Doing security reviews for this content can be a real nightmare.

To be fair though I have no issue with using LLM created code with the caveat being YOU MUST BE UNDERSTAND IT. If you don’t understand it enough to be able to review it you’re effectively copying and pasting Stack Overflow

[standardUser]

At least with Stack Overflow there's upvotes and comments to give me some confidence (sometimes too much confidence). With LLMs I start hyper-skeptical and remain hyper-skeptical - there's really no way to develop confidence in it because the mistakes can be so random and dissimilar to the errors we're used to parsing in human-generated content.

Having said that, LLMs have saved me a ton of time, caught my dumb errors and typos, helped me improve code performance (especially database queries) and even clued me into to some better code-writing conventions/updated syntax that I hadn't been using.

[stackskipton]

Also with most Stack Overflow copy and pasted code, you can Google the suspicious code, find the link to it and read over the question/comments and somewhat grok the decision and maybe even find a fix in the comments.

Most AI Code does not have prompts and even if it does, there is not guarantee that same prompt will produce the same output so it's like reading human code except human can't explain themselves even if you have access to them.

[thayne]

In my experience, fixing code generated by AI is often more work than writing it myself the right way.

And even uf you understand the code, that doesn't mean it is maintainable code.

[Helmut10001]

This. I only use AI for the things I don't want to do: tax, reporting, filling forms etc. You name it. For anything attributed to me as a creative person, I write myself. Volume vise, this is comparable to the 80% (tax, reporting, filling forms) and 20% (creativity, thinking, focusing).

[BoiledCabbage]

> AI is built essentially on averages.

It is, but that also means if you prompt it correctly it will give you the answer of the average graduate student working on theoretical physics, or the average expert on the historical inter-cultural conflict of the country you are researching. Averages can be very powerful as well.

[andy99]

Research has no average, there's opinion and experience and nuance. This whole "graduate level" thing (no idea if that's what the parent comment refers to) is so stupid, and marketing at people who have never done research or advanced studies.

Getting an average response by necessity gives you something dumbed down and smoothed over that nobody in the field would actually write (except maybe to train and LLM or contribute an encyclopedia entry).

Not that having general knowledge is a bad thing, but LLM output is not representative of what a researcher would do or write.

[Jach]

One thing the "graduate level" concept reminds me of is Terence Tao's semi endorsement almost a year ago: https://mathstodon.xyz/@tao/113132502735585408 People quote the "The experience seemed roughly on par with trying to advise a mediocre, but not completely incompetent, (static simulation of a) graduate student." part but ignore all the rest of the nuance in the thread like "It may only take one or two further iterations of improved capability (and integration with other tools, such as computer algebra packages and proof assistants) until the level of "(static simulation of a) competent graduate student" is reached, at which point I could see this tool being of significant use in research level tasks." or "I inadvertently gave the incorrect (and potentially harmful) impression that human graduate students could be reductively classified according to a static, one dimensional level of “competence”."

[ofjcihen]

I see this argument all the time. That the user must not be prompting correctly.

In my experience the way you prompt is less important than the “averageness” of the answer you’re looking for.

[Jach]

Talking about averages is really misleading. Talk about capabilities instead, framed in tool language if you must.

Quoting https://buttondown.com/hillelwayne/archive/ai-is-a-gamechang... about https://zfhuang99.github.io/github%20copilot/formal%20verifi... "In the post, Cheng Huang claims that Azure successfully used LLMs to examine an existing codebase, derive a TLA+ spec, and find a production bug in that spec." This is not the behavior of the "average" anything.

[ofjcihen]

Take it from someone in the business of exploiting race conditions for money: that’s about as average as you can get. Additionally, whatever Azure is considering “traditional” methods may be bare bones poorly optimized automated code reviews given the egregious issues they’ve had in the past.

As a side note:LLMs by definition do not demonstrate “understanding” of anything.

[1vuio0pswjnm7]

Autocomplete allows one to see what strings others have written, typed, or dictated. That can be useful, no doubt. For one, it saves time typing those strings oneself.

But claiming those strings as one's own is a bridge too far. Of course one might want to avoid inadvertently creating strings that others have already created. Autocomplete can prevent that. But people will inevitably need to create new strings that no one else has created before. There is no substitute for the thinking behind the creation of new strings. Recombining old strings is not a substitute.

"AI" is being marketed as a substitute. Recombination of past work is not, by itself, new work or new thinking. As with autocomplete, there are limits to its usefulness.

For software developers who hate "intellectual property" and like to take ideas from others, this may be 100% acceptable. But for non-software developers who seek originality, it might fall short.

When the people invested in "AI", e.g., Silicon Valley wonks, start throwing around terms like "intelligence" to describe a new type of autocomplete, when they fake demos to mislead people about its limits, then some people are going to lose interest. Software developers betting on "AI" may not be among them. The irony is that software development is already so rife with economically justified mindless copying and unoriginality that software quality is in a free fall. "AI" is only going to supercharge the race to the bottom.

Like it or not, the market wants "bad code". It loves mindless copying. It has no notion of "code quality". It demands minimisation of "developer time". Perhaps "AI" will deliver.