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

361–370 of 420 posts

Re: My AI Adoption Journey

#361

Post by HarHarVeryFunny »

claytongulick wrote: post #324

I know I'm in the minority here, but I've been finding AI to be increasingly useless. I'd already abandoned it for generating code, for all the reasons everyone knows, that don't need to be rehashed. I was still in the camp of "It's a better google" and can save me time with research. The issue it, at this point in my career (30+ years) the questions I have are a bit more nuanced and complex. They aren't things like…

I can relate as far as asking AI for advice on complex design tasks. The fundamental problem is that it is still basically a pattern matching technology that "speaks before thinking". For shallow problems this is fine, but where it fails is when it a useful response would require it to have analyzed the consequences of what it is suggesting, although (not that it helps) many people might respond in the same way - with whatever "comes to mind".

I used to joke that programming is not a career - it's a disease - since practiced long enough it fundamentally changes the way you think and talk, always thinking multiple steps ahead and the implications of what you, or anyone else, is saying. Asking advice from another seasoned developer you'll get advice that has also been "pre-analyzed", but not from an LLM.

Re: My AI Adoption Journey

#362

Post by randusername »

> I'm a software craftsman

This perspective is why I think this article is so refreshing.

Craftsmen approach tools differently. They don't expect tools to work for them out-of-the-box. They customize the tool to their liking and reexamine their workflow in light of the tool. Either that or they have such idiosyncratic workflows they have to build their own tools.

They know their tools are custom to _them_. It would be silly to impose that everyone else use their tools-- they build different things!

Re: My AI Adoption Journey

#363

Post by jedberg »

datsci_est_2015 wrote: post #256
lawgimenez wrote: post #230

Earlier quoted context omitted.

Can't believe you don't know who the author is my man.

Generally don’t pay attention to names unless it’s someone like Torvalds, Stroustrop, or Guido. Maybe this guy needs another decade of notoriety or something.

The author is the founder of Hasicorp. He created Vault and Terraform, among others.

Re: My AI Adoption Journey

#364

Post by chrysoprace »

wiether wrote: post #252
chrysoprace wrote: post #93

Earlier quoted context omitted.

I think for a lot of people the turn off is the constant churn and the hype cycle. For a lot of people, they just want to get things done and not have to constantly keep on top of what's new or SOTA. Are we still using MCPs or are we using Skills now? Not long ago you had to know MCP or you'd be left behind and you definitely need to know MCP UI or you'll be left behind. I think. It just becomes really tiring, especi…

> Or if a company provides a model that's as good value that can be used with OpenCode. OpenAI's Codex?

From everything I've heard, Claude Code is still better at coding and better value (subscription) but I'm happy to be proven wrong.

Re: My AI Adoption Journey

#365

Post by nosianu »

tptacek wrote: post #342
nosianu wrote: post #245

Earlier quoted context omitted.

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.

[flagged]

Re: My AI Adoption Journey

#366

Post by vazma »

I respect Hashimoto for his contributions in the field, but to be honest, I am fed up with posts talking about using AI in ways that are impossible for most people due to high costs. I want to see more posts on cost-effective techniques, rather than just another guy showing off how he turned a creative 'burning-time' hobby into a 'burning-money' one.

Re: My AI Adoption Journey

#367

Post by wtetzner »

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.

The input to LLMs is natural language. Natural language is ambiguous. No amount of LLM improvements will change that.

Re: My AI Adoption Journey

#368

Post by tonfa »

D-Machine wrote: post #333
bonesss wrote: post #227

Earlier quoted context omitted.

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…

> I don't even see how an LLM (or frankly any recipe) that is a summary / condensation of various recipes can ever be good

It's funny, I actually know quite a few (totally non tech) people who uses (and like using) LLMs for recipes/recipes ideas.

They probably have enough experience to push back when there's a bad idea, or figure out missing steps/follow up.

Thinking about it, it sounds a bit like LLM usage for coding where an experienced programmer can get more value out of it.

Re: My AI Adoption Journey

#369

Post by mi_lk »

lysace wrote: post #321
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 current realistic lower bound for actual work is the $100/€90/month Claude Max ("5x") plan. It allows roughly enough usage for a typical working month (4.25 x 40-50h). "Single-threaded", interactive usage with normal human breaks, sort of. There are two usage quota windows to be aware of: 5h and 7d. I use https://github.com/richhickson/claudecodeusage (Mac) to keep track of the status. It shows green/yellow/red a…

is there a guidance on when an API v.s. a subscription is a better deal?

Re: My AI Adoption Journey

#370

Post by bsder »

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.

> 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

Is it? Sure, the chatbot style maxes at $200/month. I consider that ... not unreasonable ... for a professional tool. It doesn't make me happy, but it's not horrific.

The article, however, explicitly pans the chatbot style and is extolling the API style being accessed constantly by agents, and that has no upper bound. Roughly $10-ish per Megatokens. $10-ish per 1K web searches. etc.

This doesn't sound "minimal" to me. This sounds like every single "task" I kick off is $10. And it can kick those tasks and costs off very quickly in an automated fashion. It doesn't take many of those tasks before I'm paying more than an actual full developer.

Ref: https://claude.com/pricing#api

Post reply on HN