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

351–360 of 420 posts

Re: My AI Adoption Journey

#351

Post by wtetzner »

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…

> The compiler metaphor is simply incorrect

If an LLM was analogous to a compiler, then we would be committing prompts to source control, not the output of the LLM (the "machine code").

Re: My AI Adoption Journey

#352

Post by wtetzner »

kyoji wrote: post #314

This was a great post, one of the best I've seen on this topic at HN. But why is the cost never discussed or disclosed in these conversations? I feel like I'm going crazy, there is so much written extolling the virtues of these tools but with no mention of what it costs to run them now. It will surely only get more expensive from here!

> But why is the cost never discussed or disclosed in these conversations?

And not just the monetary cost of accessing the tools, but the amount of time it takes to actually get good results out. I strongly suspect that even though it feels more productive, in many cases things just take longer than they would if done manually.

I think there are really good uses for LLMs, but I also think that people are likely using them in ways that feel useful, but end up being more costly than not.

Re: My AI Adoption Journey

#353

Post by i_love_retros »

AI chat for research is great and really helps me.

I just don't need the AI writing code for me, don't see the point. Once I know from the ai chat research what my solution is I can code it myself with the benefit I then understand more what I am doing.

And yes I've tried the latest models! Tried agent mode in copilot! Don't need it!

Re: My AI Adoption Journey

#355

Post by Havoc »

erelong wrote: post #348

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…

Suspect the sweet spot also depends on the objective. If it’s a personal tool where you are the primary user then vibe coding all the way. You can describe requirements precisely and if it breaks there are no angry customers.

Something with actual users needs a bit more care

Re: My AI Adoption Journey

#356

Post by i_love_retros »

jjice wrote: post #317
i_love_retros wrote: post #299

Earlier quoted context omitted.

Billionaires also tend to have a vested interest in the tech being hyped and adopted, after all one doesn't become a billionaire without investments.

Define investment in this case. He's the cofounder of HashiCorp. I guess you could refer to his equity as an investment here, but I don't really think it tracks the same in this context. He may have a vested interest, but he did cofound HashiCorp as an engineer that actually developed the products, so I find his insight at least somewhat valuable.

Well did he become a billionaire from hashicorp alone or did he invest e.g. millions in stocks (like perhaps ai stocks) to become a billionaire

Re: My AI Adoption Journey

#357

Post by e40 »

swordsith wrote: post #219
e40 wrote: post #82

For those of working on large proprietary, in fringe languages as well, what can we do? Upload all the source code to the cloud model? I am really wary of giving it a million lines of code it’s never seen.

I've found mostly for context reasons its better to just have a grand overview of the systems and how they work together and feed that to the agent as context, it will use the additional files it touches to expand its understanding if you prompt well.

Does this essentially give the companies controlling these models access to our source code? That is, it goes into training future versions of the model?

Re: My AI Adoption Journey

#358

Post by hollowturtle »

maqnius wrote: post #325
hollowturtle wrote: post #226

I don't understand how Agents make you feel productive. Single/Multiple agents reading specs, specs often produced with agents itself and iterated over time with human in the loop, a lot of reviewing of giant gibberish specs. Never had a clear spec in my life. Then all the dancing for this apperantly new paradigm, of not reviewing code but verifying behaviour, and so many other things. All of this to me is a total UN…

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?

Re: My AI Adoption Journey

#359

Post by causal »

> Always Have an Agent Running

I'm a huge believer in AI agent use and even I think this is wrong. It's like saying "always have something compiling" or "make sure your Internet is always downloading something".

The most important work happens when an agent is not running, and if you spend most of your time looking for ways to run more agents you're going to streetlight-effect your way into solving the wrong problems https://en.wikipedia.org/wiki/Streetlight_effect

Re: My AI Adoption Journey

#360

Post by fusslo »

kyoji wrote: post #314

This was a great post, one of the best I've seen on this topic at HN. But why is the cost never discussed or disclosed in these conversations? I feel like I'm going crazy, there is so much written extolling the virtues of these tools but with no mention of what it costs to run them now. It will surely only get more expensive from here!

the first time I did work as the article suggests I used my monthly allowance in a day.

Apparently out of 3-5k people with access to our AI tools, there's fewer than a handful of us REALLY using it. Most are asking questions in the chatbot style.

Anyway, I had to ask my manager, the AI architect, and the Tooling Manager for approval to increase my quota.

I asked everyone in the chain how much equivalent dollars I am allocated, and how much the increase was and no one could tell me.

Post reply on HN