Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The insecure evangelism of LLM maximalists

lewiscampbell.tech

Post reply on HN
Print view View original

161–170 of 295 posts

Re: The insecure evangelism of LLM maximalists

#161

Post by fourthark »

mkroman wrote: post #156
visarga wrote: post #148

Earlier quoted context omitted.

Untested undocumented LLM code is technical debt, but if you do specs and tests it's actually the opposite, you can go beyond technical debt and regenerate your code as you like. You just need testing to be so good it guarantees the behavior you care about, and that is easier in our age of AI coding agents.

> but if you do specs and tests it's actually the opposite, you can go beyond technical debt and regenerate your code as you like. Having to write all the specs and tests just right so you can regenerate the code until you get the desired output just sounds like an expensive version of the infinite monkey theorem, but with LLMs instead of monkeys.

You can have it write the specs and tests, too, and review and refine them much faster than you could write them.

Re: The insecure evangelism of LLM maximalists

#162

Post by SchemaLoad »

lekevicius wrote: post #73
perardi wrote: post #19

5 anti-AI posts on the home page of Hacker News…yeah, plenty of insecure evangelism amongst the skeptics, too.

Is there enough of new blood on HN? For me it was the best place, my favorite website, when I was entering startup scene. Loved it. I don't think a lot of young founders I know ever go here...

They are on LinkedIn now posting hustle bro posts about how they wake up at 4 am for yoga while Claude Code generates everything for them.

Re: The insecure evangelism of LLM maximalists

#163

Post by NomDePlum »

kokanee wrote: post #141
rudedogg wrote: post #3

Hearing people on tech twitter say that LLMs always produce better code than they do by hand was pretty enlightening for me. LLMs can produce better code for languages and domains I’m not proficient in, at a much faster rate, but damn it’s rare I look at LLM output and don’t spot something I’d do measurably better. These things are average text generation machines. Yes you can improve the output quality by writing a…

> These things are average text generation machines. Funny... seems like about half of devs think AI writes good code, and half think it doesn't. When you consider that it is designed to replicate average output, that makes a lot of sense. So, as insulting as OP's idea is, it would make sense that below-average devs are getting gains by using AI, and above-average devs aren't. In theory, this situation should raise t…

> it would make sense that below-average devs are getting gains by using AI

They are certainly opening more PRs. Being the gate and last safety check on the PRs is certainly driving me in the opposite direction.

Re: The insecure evangelism of LLM maximalists

#164

Post by SchemaLoad »

selfhoster11 wrote: post #37
WolfeReader wrote: post #32

Earlier quoted context omitted.

Given how much energy LLMs use, I'd greatly prefer not to let the results speak for themselves.

Far less than you'd think for local LLMs.

Local LLMs that you can run on consumer hardware don't really do anything though. They are amusing, maybe you could use them for basic text search, but they don't have any real knowledge like the hosted ones do.

Re: The insecure evangelism of LLM maximalists

#165

Post by blibble »

CapsAdmin wrote: post #79
rudedogg wrote: post #3

Hearing people on tech twitter say that LLMs always produce better code than they do by hand was pretty enlightening for me. LLMs can produce better code for languages and domains I’m not proficient in, at a much faster rate, but damn it’s rare I look at LLM output and don’t spot something I’d do measurably better. These things are average text generation machines. Yes you can improve the output quality by writing a…

I've been playing with vibe coding a lot lately and I think in most cases, the current SOTA LLM's don't produce code that I'd be satisfied with. I kind of feel like LLM's are really really good at hacking on a messy and fragile structure, because they can "keep track many things in their head" BUT An LLM can write a PNG decoder that works in whatever language I choose in one or a few shots. I can do that too, but it…

> Maybe objectively it does, but can we convince them that it does?

how long would you give our current civilisation if quality of software ceased to be important for:

  - medical devices
  - aircraft
  - railway signalling systems
  - engine management systems
  - the financial system
  - electrical grid
  - water treatment
  - and every other critical system
unless "AI" dies, we're going to find out

Re: The insecure evangelism of LLM maximalists

#166

Post by rtpg »

wild_egg wrote: post #41
rudedogg wrote: post #3

Hearing people on tech twitter say that LLMs always produce better code than they do by hand was pretty enlightening for me. LLMs can produce better code for languages and domains I’m not proficient in, at a much faster rate, but damn it’s rare I look at LLM output and don’t spot something I’d do measurably better. These things are average text generation machines. Yes you can improve the output quality by writing a…

After a certain experience level though, I think most of us get to the point of knowing what that difference in quality actually matters. Some seniors love to bikeshed PRs all day because they can do it better but generally that activity has zero actual value. Sometimes it matters, often it doesn't. Stop with the "I could do this better by hand" and ask "is it worth the extra 4 hours to do this by hand, or is this ac…

now sometimes that's 4 hours, but I've had plenty of times where I'm "racing" people using LLMs and I basically get the coding done before them. Once I debugged an issue before the robot was done `ls`-ing the codebase!

The shape of the problem is super important in considering the results here

Re: The insecure evangelism of LLM maximalists

#167

Post by caycep »

throwawayffffas wrote: post #107
rudedogg wrote: post #3

Hearing people on tech twitter say that LLMs always produce better code than they do by hand was pretty enlightening for me. LLMs can produce better code for languages and domains I’m not proficient in, at a much faster rate, but damn it’s rare I look at LLM output and don’t spot something I’d do measurably better. These things are average text generation machines. Yes you can improve the output quality by writing a…

> Hearing people on tech twitter say that LLMs always produce better code than they do by hand was pretty enlightening for me. That's hilarious LLM code is always very bad. It's only merit is it occasionally works. > LLMs can produce better code for languages and domains I’m not proficient in. I am sure that's not true.

I think it says more about who's still on tech twitter vs. anything about the llm....

Re: The insecure evangelism of LLM maximalists

#168

Post by rectang »

bryanlarsen wrote: post #139
throwawayffffas wrote: post #119

Earlier quoted context omitted.

That's funny that's all the things I don't trust it to do. I actually use it the other way around, give it a big non-specific task, see if it works, specify better, retry, throw away 60% - 90% of the generated code, fix bugs in a bunch of places and out comes an implemented feature.

Agreed. Claude is horrible at munging git history and can destroy the thing I depend on to fix Claude's messes. I always do my git rebasing by hand. The first iteration of Claude code is usually a big over-coded mess, but it's pretty good at iterating to clean it up, given proper instruction.

I give the agent the following standing instructions:

"Make the smallest possible change. Do not refactor existing code unless I explicitly ask."

That directive cut down considerably on the amount of extra changes I had to review. When it gets it right, the changes are close to the right size now.

The agent still tries to do too much, typically suggesting three tangents for every interaction.

Re: The insecure evangelism of LLM maximalists

#169

Post by falloutx »

kiernanmcgowan wrote: post #5

LLMs are really great at copy/pasting answers from stack overflow and fitting them to work in a given system. If your work is outside what is answerable on stack overflow you're going to end up fighting the results constantly. Front end pages like a user settings page? Done. One shottable. Nuanced data migration problems specific to your stack? You're going to be yelling at the agent. > LLM evangelists - are you will…

> Front end pages like a user settings page? Done. One shottable.

This is only one shottable if you are high paced startup or you don't care enough. In real world software, you would need to make it accessible, store data in a complaint way, hook up translations, make sure all inputs are validated and do some usability testing.

Re: The insecure evangelism of LLM maximalists

#170

Post by falloutx »

anonym29 wrote: post #76

I don't mind weighing in as someone who could fairly be categorized as both an LLM evangelist and "not an experienced dev". It's a lot like why I've been bullish on Tesla's approach to FSD even as someone who owned an AP1 vehicle that objectively was NOT "self-driving" in any sense of the word: it's less about where the technology is right now , or even the speed the technology is currently improving at, and more abo…

5 years? That seems generous. We are being threatened this summer (in some companies its gonna be even earlier)
Post reply on HN