Live data from Hacker News

Generative AI coding tools and agents do not work for me

blog.miguelgrinberg.com

411–420 of 464 posts

Re: Generative AI coding tools and agents do not work for me

#411

Earlier quoted context omitted.

> I think people are getting addicted to not having to expend brain energy to solve problems, and they're mistaking that for productivity. I think that's a really elegant way to put it. Google Research tried to measure LLM impacts on productivity in 2024 [1]. They gave their subjects an exam and assigned them different resources (a book versus an LLM). They found that the LLM users actually took more time to finish t…

You’re twisting results. Just because they took more time doesn’t mean their productivity went down. On the contrary, if you can perform expert task with much less mental resources (which 99% of orgs should prioritize for) then it is an absolute win. Work is extremely mentally draining and soul crushing experience for majority of people, if AI can lower that while maintaining roughly same result with subjects allocat…

They took more time and, on average, had fewer correct answers. Decreased "productivity" was the language the researchers used.

Re: Generative AI coding tools and agents do not work for me

#412

> Another common argument I've heard is that Generative AI is helpful when you need to write code in a language or technology you are not familiar with. To me this also makes little sense. I'm not sure I get this one. When I'm learning new tech I almost always have questions. I used to google them. If I couldn't find an answer I might try posting on stack overflow. Sometimes as I'm typing the question their search wo…

For one-offs, sure! Go for it. For production/things you will have to manage long-term I would recommend learning some of the space given the output of AI and your capability to surpass that pretty quickly.

Re: Generative AI coding tools and agents do not work for me

#413

Earlier quoted context omitted.

You’re twisting results. Just because they took more time doesn’t mean their productivity went down. On the contrary, if you can perform expert task with much less mental resources (which 99% of orgs should prioritize for) then it is an absolute win. Work is extremely mentally draining and soul crushing experience for majority of people, if AI can lower that while maintaining roughly same result with subjects allocat…

If I follow what you are saying, employers won't see any benefits, but employees, while they will take the same time and create the same output in the same amount of time, will be able to do so at a reduced mental strain? Personally, I don't know if this is always a win, mostly because I enjoy the creative and problem solving aspect of coding, and reducing that to something that is more about prompting, correcting, a…

Great tools should be: 1. More efficient 2. Better Quality 3. Allow you to be lazier

AI hits 3, but not the other two. Given the current human condition, this is a dangerous combination! It will win, but at the cost of the other two.

Re: Generative AI coding tools and agents do not work for me

#414
post #272

Earlier quoted context omitted.

If I follow what you are saying, employers won't see any benefits, but employees, while they will take the same time and create the same output in the same amount of time, will be able to do so at a reduced mental strain? Personally, I don't know if this is always a win, mostly because I enjoy the creative and problem solving aspect of coding, and reducing that to something that is more about prompting, correcting, a…

Steelmanning their argument, employers will see benefits because while the employee might be more productive than with an LLM in the first two hours of the day, the cognitive load reduces their productivity as the day goes on. If employees are able to function at a higher level for longer during their day with an LLM, that should benefit the employer.

I think we are all working without data here, it's all conjecture.

I went with OP's hypothesis that you are not faster, you throw things at the wall, wait, and see if it sticks, or re-throw it until it does. This reduces your cognitive load, but might not actually make you more productive.

I'm assuming here that "you are not more productive" already accounted for what you are saying. Like in a 8h day, without AI, you get X done, and with AI you also get X done, likely because during the peak productivity hours of your day you get more done without AI, but when you are mentally tired you get less done, and it evens out with a full day of AI work.

There's no data here, it's all just people's intuition and impression, not actually measuring their productivity in any quantifiable way.

What you hypothesize could also be true, it the mental load is reduced, can you sustain a higher productivity for longer? We don't know, maybe.

Re: Generative AI coding tools and agents do not work for me

#415
post #228

Earlier quoted context omitted.

If I follow what you are saying, employers won't see any benefits, but employees, while they will take the same time and create the same output in the same amount of time, will be able to do so at a reduced mental strain? Personally, I don't know if this is always a win, mostly because I enjoy the creative and problem solving aspect of coding, and reducing that to something that is more about prompting, correcting, a…

And how long have you been doing this? Because that sounds naive. After doing programming for a decade or two, the actual act of programming is not enough to be ”creative problem solving”, it’s the domain and set of problems you get to apply it to that need to be interesting. >90% of programming tasks at a company are usually reimplementing things and algorithms that have been done a thousand times before by others,…

I think you make a good point. There is an issue of people talking over each other. The reality is, we don't all do the same work. It's possible my job and someone else's involves having to deliver very different code where the challenges to it differ.

One person might feel like their job is just coding the same CRUD app over and over re-skinned. Where-as I feel my job is to simplify code by figuring out better structures and abstractions to model the problem domain which together solve systemic issues with the delivered system and enables more features to work together without issue and be added to the system, as well as making changes and new features/use-cases delivery faster.

The latter I find a creative exercise, the former I might get bored and wish AI could automate it away.

I think what it is you are tasked with doing exactly at your job will also mean that your use of agentic AI actually makes you more productive or not.

Re: Generative AI coding tools and agents do not work for me

#416
AI is like a factory, which produces goods. People are happy: they have the goods and can improve their lifes. These people see only the goods and are really surprised why some people talk about AI being not useful for them or even having a negative effect.

The reality is, that this factory is also leaking toxic waste into the nature. There are people who already see this, and try to warn the rest. Of course, the factory doesn’t care, unless it’s forced to.

The toxic waste started to accumulate. People start to get sick… but nobody cares.

Re: Generative AI coding tools and agents do not work for me

#417

> Another common argument I've heard is that Generative AI is helpful when you need to write code in a language or technology you are not familiar with. To me this also makes little sense. I'm not sure I get this one. When I'm learning new tech I almost always have questions. I used to google them. If I couldn't find an answer I might try posting on stack overflow. Sometimes as I'm typing the question their search wo…

ChatGPT and Gemini literally only know the answer because they read StackOverflow. Stack Overflow only exists because they have visitors. What do you think will happen when everyone is using the AI tools to answer their questions? We'll be back in the world of Encyclopedias, in which central authorities spent large amounts of money manually collecting information and publishing it. And then they spent a good amount o…

We'll be back in the world of Encyclopedias

On a related note, I recently learned that you can still subscribe to the Encyclopedia Britannica. It's $9/month, or $75/year.

Considering the declining state of Wikipedia, and the untrustworthiness of A.I., I'm considering it.

Re: Generative AI coding tools and agents do not work for me

#418
post #410

AI offers many solutions and also brings many problems. Some people like to see only the good side and act, as if there would be no bad side. One of the biggest problem I see with AI is, that it makes people used to NOT to think. It takes lots of time and energy to learn to program and design complex software. AI doesn’t solve this - humans to be able to supervise need to have these skills. But why would new programm…

Agreed. StackOverflow makes it easier not think and copy-paste. Autocomplete makes it easier to not think and make typos (Hopefully you have static typing). Package management makes it easier to not think and introduce heavy dependencies. C makes it easier to not think and forget to initialize variables. I make it easier to not think and read without considering evil (What if every word I say has evil intention and e…

Everything you said, except for Stackoverflow is an abstraction.

Abstractions are making you think of different things. They “hide” some detail and allow you to focus on something else. Of course, the abstraction has its price.

This is true for AI too. The price is the problem.

Re: Generative AI coding tools and agents do not work for me

#419
post #128

Earlier quoted context omitted.

This is radical and healthy way to do it. Obviously wrong — reject. Obviously right — accept. In any other case — also reject, as non-obvious. I guess it is far removed from the advertized use case. Also, I feel one would be better off having auto-complete powered by LLM in this case.

> Obviously right — accept. I don't think code is ever "obviously right" unless it is trivially simple

Seriously. I've taken to thinking of most submitters as adversarial agents--even the ones I know to be well-meaning humans. I've seen enough code that looks obviously right and yet has some subtle bug (that I then have to tease apart and fix), or worse, a security flaw that lies in wait like a sleeper cell for the right moment to unleash havoc and ruin your day.

So with this "obviously right" rubric I would wind up rejecting 95% of submissions, which is a waste of my time and energy. How about instead I just write it myself? At least then I know who's responsible for cleaning up after the it.

Re: Generative AI coding tools and agents do not work for me

#420

> But interns learn and get better over time. The time that you spend reviewing code or providing feedback to an intern is not wasted, it is an investment in the future. The intern absorbs the knowledge you share and uses it for new tasks you assign to them later on. This is the piece that confuses me about the comparison to a junior or an intern. Humans learn about the business, the code, the history of the system.…

Interns usually CARE as well.
Post reply on HN