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

331–340 of 420 posts

Re: My AI Adoption Journey

#331

Post by lysace »

mbesto wrote: post #330
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!

Honestly, the costs are so minimal and vary wildly relative to the cost of a developer that it's frankly not worth the discussion...yet. The reality is the standard deviation of cost is going to oscillate until there is a common agreed upon way to use these tools.

Yes, but the lack of clear pricing probably makes people think it's more expensive than it actually is. (It did so to me.)

There is nothing quantifiable here: https://claude.com/pricing

Pro: "Everything in Free, plus: More usage"

Max: "Choose 5x or 20x more usage than Pro"

Wow, 5x or 20x more of "more". That's some masterful communication right there.

Re: My AI Adoption Journey

#332

Post by tjr »

allworms wrote: post #95
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…

> We don't call architects 'vibe architects' even though they copy-paste 4/5th of your next house and use a library of things in their work! > We don't call builders 'vibe builders' for using earth-moving machines instead of a shovel... > When was the last time you reviewed the machine code produced by a compiler? Sure, because those are categorically different. You are describing shortcuts of two classes: boilerplat…

Delegation, yes.

I do not see LLM coding as another step up on the ladder of programming abstraction.

If your project is in, say, Python, then by using LLMs, you are not writing software in English; you are having an LLM write software for you in Python.

This is much more like delegation of work to someone else, than it is another layer in the machine-code/assembly/C/Python sort of hierarchy.

In my regular day job, I am a project manager. I find LLM coding to be effectively project management. As a project manager, I am free to dive down to whatever level of technical detail I want, but by and large, it is others on the team who actually write the software. If I assign a task, I don't say "I wrote that code", because I didn't; someone else did, even if I directed it.

And then, project management, delegating to the team, is most certainly nondeterministic behavior. Any programmer on the team might come up with a different solution, each of which works. The same programmer might come up with more than one solutions, all of which work.

I don't expect the programmers to be deterministic. I do expect the compiler to be deterministic.

Re: My AI Adoption Journey

#333

Post by D-Machine »

bonesss wrote: post #227
andai wrote: post #154

Earlier quoted context omitted.

This is obviously besides the point but I did blindly follow a wiener schnitzel recipe ChatGPT made me and cooked for a whole crew. It turned out great. I think I got lucky though, the next day I absolutely massacred the pancakes.

Recent experiments with LLM recipes (ChatGPT): missed salt in a recipe to make rice, then flubbed whether that type of rice was recommended to be washed in the recipe it was supposedly summarizing (and lied about it, too)… Probabilistic generation will be weighted towards the means in the training data. Do I want my code looking like most code most of the time in a world full of Node.js and PHP? Am I better served by…

Pro-tip: Do NOT use LLMs to generate recipes, use them to search the internet for a site with a trustworthy recipe, for information on cooking techniques, science, or chemistry, or if you need ideas about pairings and/or cooking theory / conventions. Do not trust anything an LLM says if it doesn't give a source, it seems people on the internet can't cook for shit and just make stuff up about food science and cooking (e.g. "searing seals in the moisture", though most people know this is nonsense now), so the training data here is utterly corrupt. You always need to inspect the sources.

I don't even see how an LLM (or frankly any recipe) that is a summary / condensation of various recipes can ever be good, because cooking isn't something where you can semantically condense or even mathematically combine various recipes together to get one good one. It just doesn't work like that, there is just one secret recipe that produces the best dish, and the way to find this secret recipe is by experimenting in the real world, not by trying to find some weighting of a bunch of different steps from a bunch of different recipes.

Plus, LLMs don't know how to judge quality of recipes at all (and indeed hallucinate total nonsense if they don't have search enabled).

Re: My AI Adoption Journey

#334

Post by mbesto »

latexr wrote: post #259
tptacek wrote: post #39

Earlier quoted context omitted.

As long as we're on the same page that what he's describing is itself a miracle .

It’s not. A miracle is “an event that is inexplicable by natural or scientific laws and accordingly gets attributed to some supernatural or preternatural cause”. Could we please stop trivialising and ignoring the meaning of words?

The word miracle itself is hyperbolic in nature...it's meant to enchant and not to be used literal or concretely.

No need to be pedantic here, there is a large cohort of the population that seemingly never thought a robot would be able to write usable code ("inexplicable by natural or scientific laws") and now here we are seeing that happen ("hey this must be preternatural! there is no other explanation")

Re: My AI Adoption Journey

#335

Post by lawn »

jon_north wrote: post #311
jplusequalt wrote: post #309

Earlier quoted context omitted.

>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/

And yet, the average salary of an IT worker in the US is somewhere between 104 and 110k. Since we're discussing coders here, and IT workers tend to be at the lower end of that, maybe there is some context you didn't consider?

And yet, the difference between average and median isn't understood.

Re: My AI Adoption Journey

#336

Post by Scene_Cast2 »

bayindirh wrote: post #285
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 and processors are deterministic by design . LLMs are non-deterministic by design . It's not apples vs. oranges. They are literally opposite of each other.

Just to nitpick - compilers (and, to some extent, processors) weren't deterministic a few decades ago. Getting them to be deterministic has been a monumental effort - see build reproducibility.

Re: My AI Adoption Journey

#337

Post by fullstackchris »

tmtvl wrote: post #217
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 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

Re: My AI Adoption Journey

#338

Post by oblio »

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…

> All of that is simply common sense.

Is that why we have legal codes spanning millions of pages?

Re: My AI Adoption Journey

#339

Post by nutjob2 »

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…

> We don't call architects 'vibe architects' even though they copy-paste 4/5th of your next house and use a library of things in their work!

Maybe, but they do it through the filter of their knowledge, experience and wisdom, not by rolling a large number of dice to execute a design.

LLMs are useful, just less useful than people think, for instance, 'technical debt' production has now become automated at an industrial scale.

Re: My AI Adoption Journey

#340

Post by ineedasername »

sampullman wrote: post #242
LiamPowell wrote: post #222

Earlier quoted context omitted.

I'm not arguing that LLMs are at a point today where we can blindly trust their outputs in most applications, I just don't think that 100% correct output is necessarily a requirement for that. What it needs to be is correct often enough that the cost of reviewing the output far outweighs the average cost of any errors in the output, just like with a compiler. This even applies to human written code and human mistakes…

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'll always need to make sure the program does what you want, rather than what you said."

Yes, making sure the program does what you want. Which is already part of the existing software development life cycle. Just as using natural language to specify work already is: It's where things start and return to over and over throughout any project. Further: LLM's frequently understand what I want better than other developers. Sure, lots of times they don't. But they're a lot better at it than they were 6 months ago, and a year ago they barely did so at all save for scripts of a few dozen lines.

Post reply on HN