Live data from Hacker News

We should be more tired than the model

vickiboykis.com

101–110 of 168 posts

Re: We should be more tired than the model

#101
post #89

Earlier quoted context omitted.

Yes, it's copy pasting but it's tedious and it adds up fast. Even the doFoo to performBar is tedious because you need to catch all instances and your find/replace script strategy might have unintended victims. In this case indeed, it's just much more convenient.

don't LSPs and IDE's help with that?

Perhaps, but do they handle all the other aspects of refactoring, too?

Re: We should be more tired than the model

#102
post #99

Earlier quoted context omitted.

The languages I use the IDE literally does this for you, perfectly, deterministically. And instantly, certainly when compared to AI.

Which languages, just out of interest?

Java has very good refactor support. I use jdt.ls which is eclipse based, but I've heard intellij is even better. I've wished for similar refactor actions in other langs.

Re: We should be more tired than the model

#103

Earlier quoted context omitted.

Yes, it's copy pasting but it's tedious and it adds up fast. Even the doFoo to performBar is tedious because you need to catch all instances and your find/replace script strategy might have unintended victims. In this case indeed, it's just much more convenient.

The languages I use the IDE literally does this for you, perfectly, deterministically. And instantly, certainly when compared to AI.

If IDE can do it, a custom tool can do it to. IntelliJ even have a built in MCP server ready to help any agent with such tasks.

Re: We should be more tired than the model

#105
post #21

Earlier quoted context omitted.

Yes. And indeed, abstraction is not what LLMs are offering.

It very much is. But it's a non-deterministic, more-lossy-than-usual abstraction: english to code.

2 different meanings of abstraction at work here.

Re: We should be more tired than the model

#106
post #99

Earlier quoted context omitted.

The languages I use the IDE literally does this for you, perfectly, deterministically. And instantly, certainly when compared to AI.

Which languages, just out of interest?

Kotlin, Java, Python, C#, Typescript. Anything that has a trustworthy and consistent pointer between code.

Ruby would be the one exception I’ve worked on in my head, and for they language, ctrl+f *usually* (but not always) finds the rest.

Ruby is particularly magical with being able to evaluate methods from dynamic strings into running, production code[0]; but otherwise, languages and capable IDEs, like IntelliJ and Visual Studio just support that. I don’t happen to use VS Code, but I assume it has basic refactor, too.

[0] Devise. https://github.com/heartcombo/devise/blob/main/lib/devise/co...

Re: We should be more tired than the model

#107

Earlier quoted context omitted.

The "right" abstraction seems like quite an art. Sometimes it's not obvious, or it takes multiple rounds of exploration and testing (I'm thinking here of the mental shift moving from HTML + JS, via jQuery, Backbone, Knockout and up to React/Vue or Angular). At all points, we thought we had reasonable abstractions for a while. Vue and Svelt, or NextJS, now are so far from the mental model of early 00s "DHTML". And I'm…

>> I’m losing control over the code I write when I work with agentic code generation > Are you saying we collectively need to get better at abstraction so that LLMs get better at abstraction (either by training, or our prompting), so that their code is easier to read? No - our current abstraction for coding agents is a loop where we express some freeform specification of a goal, then a sub loop kicks off where an llm…

[flagged]

Re: We should be more tired than the model

#108
I honestly don’t understand what people are on about.

As a dev with 40+ years behind me, I apply the same skills and tools to LLMs as I would to a small team of junior devs, except with a higher degree of rigor. I don’t feel that my skills are atrophying, in fact I’ve learned a bunch of new stuff in the process.

Depending on the work, I’m producing about 4x what I would have with a small team, and it is better code, better documented, more modularity, and less bugs than I was shipping with humans.

You have to keep a tight OODA loop, and write the code in specifications, protocols, interfaces, and implementation plans before the first executable line is put down. Iterate the code and docs together to minimize and document drift.

Treat a context window as a session. When it’s full, you start over with a new session, bring in the onboarding documentation, and go to work. I never cross context boundaries midstream, it’s always a disaster. 1m context is critical, I burn 150k just onboarding and orienting a new session.

Still shipping 4x at 1/10 the cost, and less bugs in the field (greenfield firmware development)

Re: We should be more tired than the model

#109

I don't know. I find that I'm moving up a level and improving my product-management skills while delegating most of the code to the agents. I'm still very much hands-on with the design and requirements, and I'm asking questions like, "What's our security story for XYZ?", "Are we accounting for colour-blindness?", etc. Not being down in the code allows me to prairie-dog a bit more and see the landscape better.

[flagged]
Post reply on HN