The fact that Claude knows I wrote the Virgil compiler makes it be on its best behavior when working on it. I force it to not write too much code, and to write more tests. I push back on slop and just adding another special case. It has a surprisingly deep understanding of floating point.
LLMs reward expertise
171–180 of 605 posts
Re: LLMs reward expertise
#172> Of course both are useful, but I’d rather have familiarity with the codebase than a deep general understanding of software systems. In my experience, getting that familiarity with a particular codebase in a way that isn't surface-level has always been a hands-on process. E.g. just because I know many general things about software, I need to know the particulars of the current codebase I'm in to know what is reasona…
We are having trouble onboarding engineers with AI now. Some still struggle after their first year with very basic concepts/patterns we use and make the same mistakes again and again in their PRs because they just ask Claude to fix it and never internalize it. I think using LLMs feels good at first because you can get tickets out the door faster but you never develop enough knowledge to make a big impact or become an expert in the code or business.
Re: LLMs reward expertise
#173> Of course both are useful, but I’d rather have familiarity with the codebase than a deep general understanding of software systems. In my experience, getting that familiarity with a particular codebase in a way that isn't surface-level has always been a hands-on process. E.g. just because I know many general things about software, I need to know the particulars of the current codebase I'm in to know what is reasona…
I’ve found that planning tickets with granular details (like semi specific code changes needed) is one of the best ways to get that deep knowledge of the system. Even if ultimately I delegate most of the implementation to an LLM. I also heavily verify the changes, but I find that that’s less impactful than planning a feature / tickets.
Re: LLMs reward expertise
#174I've been equating them to graphing calculators since the first LLM launched. It's an amazing tool if you know how to use it. If you don't know how to use it, it's still a tool, but you won't be doing anything amazing with it.
Re: LLMs reward expertise
#175Earlier quoted context omitted.
Code generation (by compiler) has one major difference: it's deterministic.
Here are the reported miscompilation bugs in GCC so far in 2026. The ones labeled "wrong-code". https://gcc.gnu.org/bugzilla/buglist.cgi?chfield=%5BBug%20cr I count 500+ of them.
Not sure what your point is here since wrong code doesn't mean non-deterministic. How many of these yield different results with the same input and architecture?
Re: LLMs reward expertise
#176"The most important skill in the AI era may not be prompting. It may be learning how to solve problems using the right kind of help." [1]
Context - I have over 25+ years in software, and I have this observation - being introduced to a new codebase as a human is difficult, especially depending on the scale/size and complexity of it.
Yes, you do start to learn it as you work through it, but if the scale is truly huge, it may just not be possible to fully read and understand all the code and paths etc.
I have found systems-thinkers (I believe I am one, sometimes they are architects) to be able to kind of "see the whole picture" while not knowing all the details, to the point of being able to guess how the system/software should be behaving, even if it is not actually yet. This is a hugely valuable skill and I think takes a certain kind of brain too.
That said, I think recently I may have realized something - we rely on statistics and confidence levels in order to make statements about larger populations. If we can represent a codebase as a, perhaps stratified population of code, interfaces, docs, etc. etc. etc. we may be able to take a valid random sample, review portions of the code, and make some kind of assertions about the state of the larger system - potentially, from that.
I am trying to implement this as a side project right now to see if there is anything to it, basically, a combination of AI/LLM + stats/sampling + facilitated expert human review.
I'd be interested to know if anybody is doing anything similar.
Re: LLMs reward expertise
#177Earlier quoted context omitted.
Code generation (by compiler) has one major difference: it's deterministic.
Here are the reported miscompilation bugs in GCC so far in 2026. The ones labeled "wrong-code". https://gcc.gnu.org/bugzilla/buglist.cgi?chfield=%5BBug%20cr I count 500+ of them.
That's not what "deterministic" means.
Re: LLMs reward expertise
#178> Of course both are useful, but I’d rather have familiarity with the codebase than a deep general understanding of software systems. In my experience, getting that familiarity with a particular codebase in a way that isn't surface-level has always been a hands-on process. E.g. just because I know many general things about software, I need to know the particulars of the current codebase I'm in to know what is reasona…
> If we're pushed to delegate most work to them, how do you build that expertise?
Have you ever pair programmed with someone? It's the same idea. You can be an active enough participant in the process if you wish to be and can be just as knowledgeable even if some of that knowledge lies in transactive memory. https://en.wikipedia.org/wiki/Transactive_memory As long as you have the map, and the map to the map, you don't need to retain every fact about the landscape.
Re: LLMs reward expertise
#179I've been equating them to graphing calculators since the first LLM launched. It's an amazing tool if you know how to use it. If you don't know how to use it, it's still a tool, but you won't be doing anything amazing with it.
maybe outing myself as a dinosaur, but "back in my day" the calculator came with a book that detailed exactly how to use it. Both the high level basic language and the low level system language. Not knowing how to use it is simply a failure to Read The Fucking Manual.
Re: LLMs reward expertise
#180Not sure I agree with this. The math guy at anthropic's prompts are essentially: "suppose you’ve gotta resolve the $CONJECTURE, like absolutely have to, everything depends on it. think really hard, and try to come up with a bunch of ideas to try. but remember to trust yourself and not necessarily in conventional wisdom!!" https://claude.ai/share/25740bd5-aa97-4bd7-bf58-c4df3793fda7 https://xcancel.com/__alpoge__/stat…
It's not contradictory to say that expertise is a multiplier, and that models are systematically underconfident in themselves.
It's actually refreshing when a model is sure about something because it actually tested it and has the receipts. Opus 5 seems really good about testing its own knowledge with experiments. Scientific method ftw.