Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

My AI Adoption Journey

mitchellh.com

Post reply on HN
Print view View original

371–380 of 420 posts

Re: My AI Adoption Journey

#371

Post by crazygringo »

bigstrat2003 wrote: post #140
tptacek wrote: post #97

Earlier quoted context omitted.

Ok? You still have to read the code.

You're missing the point. The point is that reading the code is more time consuming than writing it, and has always been thus. Having a machine that can generate code 100x faster, but which you have to read carefully to make sure it hasn't gone off the rails, is not an asset. It is a liability.

> The point is that reading the code is more time consuming than writing it, and has always been thus.

Huh?

First, that is definitely not true. If it were, dev teams would spend the majority of their time on code review, but they don't.

And second, even if it were true, you have to read it for code review even if it was written by a person anyways, if we're talking about the context of a team.

Re: My AI Adoption Journey

#372

Post by eikenberry »

datsci_est_2015 wrote: post #88
libraryofbabel wrote: post #53

This is such a lovely balanced thoughtful refreshingly hype-free post to read. 2025 really was the year when things shifted and many first-rate developers (often previously AI skeptics, as Mitchell was) found the tools had actually got good enough that they could incorporate AI agents into their workflows. It's a shame that AI coding tools have become such a polarizing issue among developers. I understand the reasons…

I skimmed over it, and didn’t find any discussion of: - Pull requests - Merge requests - Code review I feel like I’m taking crazy pills. Are SWE supposed to move away from code review, one of the core activities for the profession? Code review is as fundamental for SWE as double entry is for accounting. Yes, we know that functional code can get generated at incredible speeds. Yes, we know that apps and what not can b…

The primary point behind code reviews is to let author to know that someone else will look at their code. They are a psychological tool and that, AFAIK, don't work well with the AI models. If the code is important enough that you want to review it then you should probably be using a different, more interactive flow.

Mitchell talks about this in a round about way... in the "Reproduce your own work" section he obviously reviewed that code as that was the point. In the "End-of-day agents" section he talks about what he found them good for (so far). He previously wrote about how he preferred an interactive style and this article aligns with that with his progress understanding how code agents can be useful.

Re: My AI Adoption Journey

#373

Post by dysoco »

jplusequalt wrote: post #309
jon_north wrote: post #304

Earlier quoted context omitted.

If you make 10k/mo -- which is not that much!, $500 is 5% of revenue. All else held equal, if that helps you go 20% faster, it's an absolute no brainer. The question is.. does it actually help you do that, or do you go 0% faster? Or 5% slower? Inquiring minds want to know.

>If you make 10k/mo -- which is not that much!, This is the sort of statement that immediately tells me this forum is disconnected from the real world. ~80% of full time workers in the US make less than $10k a month before tax. Source: https://dqydj.com/income-percentile-calculator/

10k is more close to a yearly software developer salary in my country than a monthly one.

That being said at least the $20/mo Claude Code subscription is really worth it, and many companies are paying for the AI tools anyways.

Re: My AI Adoption Journey

#374

Post by bthornbury »

mattmanser wrote: post #206
bthornbury wrote: post #99

Earlier quoted context omitted.

Either really comprehensive tests (that you read) or read it. Usually i find you can skim most of it, but like in core sections like billing or something you gotta really review it. The models still make mistakes.

You can't skim over AI code. For even mid-level tasks it will make bad assumptions, like sorting orders or timezone conversions. Basic stuff really. You've probably got a load of ticking time bomb bugs if you've just been skimming it.

> got a load of ticking time bomb bugs

Lots and lots of tests!

Re: My AI Adoption Journey

#375

Post by maqnius »

hollowturtle wrote: post #358
maqnius wrote: post #325

Earlier quoted context omitted.

In my real life bubble, AI isn't a big deal either, at least for programmers. They tend to be very sceptical about it for many reasons, perceived productivity being only one of them. So, I guess it's much less of a thing than you would expect from media coverage and certain internet communities.

Are you hiring?

Open to applications I would say, but not completely remote. So unless you're Python or c/c++ Dev living in nrw, Germany..

Re: My AI Adoption Journey

#376

Post by alternatex »

BeetleB wrote: post #328
IhateAI wrote: post #103

Earlier quoted context omitted.

[flagged]

And not working with anyone else. AI written code is often much easier to read/review than some of my coworkers'

Can't say the same for my colleagues' AI written code. It's overtly verbose and always does more that what's required.

Re: My AI Adoption Journey

#377

Post by ianm218 »

otabdeveloper4 wrote: post #149
ianm218 wrote: post #137

Earlier quoted context omitted.

Isn’t there something off about calling predictions about the future, that aren’t possible with current tech, hype? Like people predicted AI agents would be this huge change, they were called hype since earlier models were so unreliable, and now they are mostly right as ai agents work like a mid level engineer. And clearly super human in some areas.

> ai agents work like a mid level engineer They do not. > And clearly super human in some areas. Sure, if you think calculators or bicycles are "superhuman technology". Lay off the hype pills.

> They do not. Do you have anything to back this up? This seems like a shallow dismissal. Claude Code is mostly used to ship Claude Code and Claude Cowork - which are at multi billion ARR. I use Claude Code to ship technically deep dev tools for myself for example here https://github.com/ianm199/bubble-analysis. I am a decent engineer and I wouldn't have the time or expertise to ship that.

Re: My AI Adoption Journey

#378

Post by alternatex »

fullstackchris wrote: post #337
tmtvl wrote: post #217

Earlier quoted context omitted.

I will give Claude Code a trial run if I can run it locally without an internet connection. AI companies have procured so much training data through illegal means you have to be insane to trust them in even the smallest amount.

this is such a strawman argument. what are they going to take from you? your triple forloop? they literally own the weights for a neural net that scores 77% on SWE. they dont need, nor care, about your code

They are trained on our code. Perhaps not if you don't have any of it open sourced, but it's so jarring to see someone say they don't care about our code.

Re: My AI Adoption Journey

#379

Post by senko »

wtetzner wrote: post #350
senko wrote: post #250

Earlier quoted context omitted.

> Compilers will produce working output given working input literally 100% of my time in my career. I've never personally found a compiler bug. First compilers were created in the fifties. I doubt those were bug-free. Give LLMs some fifty or so years, then let's see how (un)reliable they are.

What I don't understand about these arguments is that the input to the LLMs is natural language, which is inherently ambiguous. At which point, what does it even mean for an LLM to be reliable? And if you start feeding an unambiguous, formal language to an LLM, couldn't you just write a compiler for that language instead of having the LLM interpret it?

1) Determinism isn't the same as reliability.

Compilers are deterministic (modulo bugs), but most things in life are not, but can still be reliable.

The opposite also holds: "npm install && npm run build" can work today and fail in a year (due to ecosystem churn) even though every single component in that chain is deterministic.

2) Reliability is a continuum, not a discreet yes/no. In practice, we want things to be reliable enough (where "enough" is determined per domain).

I don't presume this will immediately change your mind, but hopefully will open your eyes to looking at this a bit differently.

Re: My AI Adoption Journey

#380

Post by eikenberry »

paracyst wrote: post #291
i_love_retros wrote: post #290

How much does it cost per day to have all these agents running on your computer? Is your company paying for it or you? What is your process of the agent writes a piece of code, let's say a really complex recursive function, and you aren't confident you could have come up with the same solution? Do you still submit it?

The guy who wrote the post is a billionaire

Is he? Source? I didn't think he made that much from the Hashicorp sale.
Post reply on HN