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

131–140 of 420 posts

Re: My AI Adoption Journey

#131

Post by QuiEgo »

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…

You read it. You now have an infinite army of overconfident slightly drunken new college grads to throw at any problem.

Some times you’re gonna want to slowly back away from them and write things yourself. Sometimes you can farm out work to them.

Code review their work as you would any one else’s, in fact more so.

My rule of thumb has been it takes a senior engineer per every 4 new grads to mentor them and code review their work. Or put another way bringing on a new grad gets you +1 output at the cost of -0.25 a senior.

Also, there are some tasks you just can’t give new college grads.

Same dynamic seems to be shaping up here. Except the AI juniors are cheap and work 24*7 and (currently) have no hope of growing into seniors.

Re: My AI Adoption Journey

#132

Post by bandrami »

chii wrote: post #130
bandrami wrote: post #107

Earlier quoted context omitted.

"Become better at intuiting the behavior of this non-deterministic black box oracle maintained by a third party" just isn't a strong professional development sell for me, personally. If the future of writing software is chasing what a model trainer has done with no ability to actually change that myself I don't think that's going to be interesting to nearly as many people.

Whether it's interesting or not is irrelevant to whether it produces usable output that could be economically valuable.

Yeah, still waiting for something to ship before I form a judgement on that

Re: My AI Adoption Journey

#133

Post by tppts »

So does everyone just run with giving full permissions on Claude code these days? It seems like I’m constantly coming back to CC to validate that it’s not running some bash that’s going to nuke my system. I would love to be able to fully step away but it feels like I can’t.

Re: My AI Adoption Journey

#134

Post by keyle »

atomicnumber3 wrote: post #116
keyle wrote: post #79

Earlier quoted context omitted.

Architects went from drawing everything on paper, to using CAD products over a generation. That's a lot of years! They're still called architects. Our tooling just had a refresh in less than 3 years and it leaves heads spinning. People are confused, fighting for or against it. Torn even between 2025 to 2026. I know I was. People need a way to describe it from 'agentic coding' to 'vibe coding' to 'modern AI assisted s…

"When was the last time you reviewed the machine code produced by a compiler?" Compilers will produce working output given working input literally 100% of my time in my career. I've never personally found a compiler bug. Meanwhile AI can't be trusted to give me a recipe for potato soup. That is to say, I would under no circumstances blindly follow the output of an LLM I asked to make soup. While I have, every day of…

You're correct, and I believe this is only a matter of time. Over time it has been getting better and will keep doing so.

Re: My AI Adoption Journey

#135

Post by apetresc »

tppts wrote: post #133

So does everyone just run with giving full permissions on Claude code these days? It seems like I’m constantly coming back to CC to validate that it’s not running some bash that’s going to nuke my system. I would love to be able to fully step away but it feels like I can’t.

Honest question, when was the last time you caught it trying to use a command that was going to "nuke your system"?

Re: My AI Adoption Journey

#136

Post by tppts »

apetresc wrote: post #135
tppts wrote: post #133

So does everyone just run with giving full permissions on Claude code these days? It seems like I’m constantly coming back to CC to validate that it’s not running some bash that’s going to nuke my system. I would love to be able to fully step away but it feels like I can’t.

Honest question, when was the last time you caught it trying to use a command that was going to "nuke your system"?

“Nuke” is maybe too strong of a word, but it has not been uncommon for me to see it trying to install specific versions of languages on my machine, or services I intentionally don’t have configured, or sometimes trying to force npm when I’m using bun, etc.

Re: My AI Adoption Journey

#137

Post by ianm218 »

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…

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.

Re: My AI Adoption Journey

#138

Post by bigstrat2003 »

keyle wrote: post #134
atomicnumber3 wrote: post #116

Earlier quoted context omitted.

"When was the last time you reviewed the machine code produced by a compiler?" Compilers will produce working output given working input literally 100% of my time in my career. I've never personally found a compiler bug. Meanwhile AI can't be trusted to give me a recipe for potato soup. That is to say, I would under no circumstances blindly follow the output of an LLM I asked to make soup. While I have, every day of…

You're correct, and I believe this is only a matter of time. Over time it has been getting better and will keep doing so.

Maybe. But it's been 3 years and it still isn't good enough to actually trust. That doesn't raise confidence that it will ever get there.

Re: My AI Adoption Journey

#139

Post by kaibee »

QuiEgo wrote: post #131
datsci_est_2015 wrote: post #88

Earlier quoted context omitted.

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…

You read it. You now have an infinite army of overconfident slightly drunken new college grads to throw at any problem. Some times you’re gonna want to slowly back away from them and write things yourself. Sometimes you can farm out work to them. Code review their work as you would any one else’s, in fact more so. My rule of thumb has been it takes a senior engineer per every 4 new grads to mentor them and code revie…

> Same dynamic seems to be shaping up here. Except the AI juniors are cheap and work 24*7 and (currently) have no hope of growing into seniors.

Each individual trained model... sure. But otoh you can look at it as a very wide junior with "infinite (only limited by your budget)" willpower. Sure, three years ago they were GPT-3.5, basically useless. And now they're Opus 4.6. I wonder what the next few years will bring.

Re: My AI Adoption Journey

#140

Post by bigstrat2003 »

tptacek wrote: post #97
datsci_est_2015 wrote: post #96

Earlier quoted context omitted.

Cool, code review continues to be one of the biggest bottlenecks in our org, with or without agentic AI pumping out 1k LOC per hour.

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.
Post reply on HN