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

341–350 of 420 posts

Re: My AI Adoption Journey

#341

Post by borroka »

keyle wrote: post #79
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…

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…

Architects went from drawing everything on paper to using CAD, not over a generation, but over a few years, after CAD and computers got good enough.

It therefore depends on where we place the discovery/availability of the product. If we place it at the time of prototype production (in the early 1960s for CAD), it took a generation (20-30 years), since by the early and mid-1990s, all professionals were already using CAD.

But if we place it at the time when CAD and personal computers became available to the general public (e.g., mid-1980s), it took no more than 5-10 years. I attended a technical school in the 1990s, and we started with hand drawing in the first two years and used CAD systems in the remaining three years of school.

The same can be said for AI. If we place the beginning of AI in the mid-1980s, the wider adoption of AI took more than a generation. If we place it at the time OpenAI developed GPT, it took 5-10 years.

Re: My AI Adoption Journey

#342

Post by tptacek »

nosianu wrote: post #245
tptacek wrote: post #97

Earlier quoted context omitted.

Ok? You still have to read the code.

That's just not what has been happening in large enterprise projects, internal or external, since long before AI. Famous example - but by no means do I want to single out that company and product: https://news.ycombinator.com/item?id=18442941 From my own experience, I kept this post bookmarked because I too worked on that project in the late 1990s, you cannot review those changes anyway. It is handled as described, y…

If your team members hand off unreviewable blobs of code and you can't keep up, your problem is team management, not technology.

Re: My AI Adoption Journey

#343

Post by wtetzner »

signatoremo wrote: post #286
sampullman wrote: post #242

Earlier quoted context omitted.

If natural language is used to specify work to the LLM, how can the output ever be trusted? You'll always need to make sure the program does what you want, rather than what you said.

You trust your natural language instructions thousand times a day. If you ask for a large black coffee, you can trust that is more or less what you’ll get. Occasionally you may get something so atrocious that you don’t dare to drink, but generally speaking you trust the coffee shop knows what you want. It you insist on a specific amount of coffee brewed at a specific temperature, however, you need tools to measure. A…

I don't think the argument is that AI isn't useful. I think the argument is that it is qualitatively different from a compiler.

Re: My AI Adoption Journey

#344

Post by wtetzner »

rootnod3 wrote: post #263
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…

Absolutely this. I am tired of that trope. Or the argument that "well, at some point we can come up with a prompt language that does exactly what you want and you just give it a detailed spec." A detailed spec is called code. It's the most round-about way to make a programming language that even then is still not deterministic at best.

And at the point that your detailed specification language is deterministic, why do you need AI in the middle?

Re: My AI Adoption Journey

#345

Post by franze »

keyle wrote: post #79
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…

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…

ad > when was the last time

i once found a bug in https://developers.google.com/closure/compiler

by borrowing a function from a not invoked Array broke the compiled code

spent a weekend in reading minified code

good times

Re: My AI Adoption Journey

#347

Post by rootnod3 »

reverius42 wrote: post #306
rootnod3 wrote: post #269

Earlier quoted context omitted.

Just create a very specific and very detailed prompt that is so specific that it starts including instructions and you came up with the most expensive programming language.

It's not great that it's the most expensive (by far), but it's also by far the most expressive programming language.

How is it more expressive? What is more expressive than Turing completeness?

Re: My AI Adoption Journey

#348

Post by erelong »

I think the sweet spot is ai-assisted chat with manual review: readily available, not as costly

agents jump ahead to the point of the user and project being out of control and more expensive

I think a lot of us still hesitate to make that jump; or at least I am not sure of a cost-effective agent approach (I guess I could manually review their output, but I could see it going off track quickly)

I guess I'd like to see more of an exact breakdown of what prompts and tools and AI are used to get ideas on if I'd use that for myself more

Re: My AI Adoption Journey

#349

Post by rootnod3 »

wtetzner wrote: post #344
rootnod3 wrote: post #263

Earlier quoted context omitted.

Absolutely this. I am tired of that trope. Or the argument that "well, at some point we can come up with a prompt language that does exactly what you want and you just give it a detailed spec." A detailed spec is called code. It's the most round-about way to make a programming language that even then is still not deterministic at best.

And at the point that your detailed specification language is deterministic, why do you need AI in the middle?

Exactly the point. AI is absolutely BS that just gets peddled by shills. It does not work. It might work for some JS bullcrao. But take existing code and ask it to add capsicum next to an ifdef of pledge. Watch the mayhem unfold.

Re: My AI Adoption Journey

#350

Post by wtetzner »

senko wrote: post #250
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…

> 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?

Post reply on HN