i used to always use proper em- and en-dashes because i care about typography, now i force myself to use a regular dash whenever even the assumption i used ai for what i wrote may impact me negatively
Various LLM Smells
281–290 of 312 posts
Re: Various LLM Smells
#282> Late last year I started writing a math blog and decided to use LLMs to polish/enhance my writing. Why would you do that in the first place? If you are just starting writing about math, I assume your goal would be to get better at it, and using LLMs is not how you get better at writing.
> Why would you do that in the first place?
free will kiddo
Re: Various LLM Smells
#283Earlier quoted context omitted.
The better workflow, and I think the one adopted by people in the second group, is to take a step back from coding, do a bit of thinking about the domain, design a better abstraction for the problem (architecture, data structure, algorithms), and then write the small amount of code you probably need. Code should grow according to need, not for its own sake. Start small, use it in the real world , and then improve it.
I agree with that, but there still is some code that eventually needs to be written and there is a subset of that code which can be generated. I think it depends on the domain as well - for example, UI code is trivially generatable by LLMs.
RAD tools like Delphi, qt creator, glade, Android Studio, Xcode’s Interface builder,… have always make it trivial to generate UI code. And there’s libraries for other concerns.
The majority of a project code are written at the beginning or when a major feature is introduced. The daily work is mostly tweaking. And you can’t tweak without a good understanding of the module.
Re: Various LLM Smells
#284Earlier quoted context omitted.
> A general pattern for LLMs is that they look really good at things you are bad at. This is true for coding, too, which I think, to a large degree, might explain the polarized differences in opinions on HN about the quality of LLM-produced code. You have the 1. "AI produces code better than I could possibly write, one shots things it would take me days to do, and has made me 10X more productive!" camp, and you have…
I've caught Claude Code generating some pretty egregious security vulnerabilities. I'm using it to build an AI RPG site and the goal is to use web assembly as a bridge between author submitted code and LLMs in order to help shore up state management at the game level. The language that I picked for the game runtime is Python. Claude really thought that the best way to validate user submitted Python was to bypass the…
> I'm using it to build an AI RPG site
I am trying something similar: basically a LLM managed MUD for people with too little time for roleplaying.
If you want to chat, hit me up at mail-from-ohsohumble@f12n.de
Re: Various LLM Smells
#285- “(The) honest caveat:” (or “genuine caveat:”, both with the colon) - “(The) honest answer:” (again, with colon) - “The thing to internalize:” - “The smoking gun:” (really, sentences that start with “The :” are a strong tell, but those four are the most prolific) - “load bearing” (when not talking about architecture) - “blast radius” (when not talking about actual explosives, but rather the effect of an event/action…
These LLM idioms are constantly being consumed every day and are bound to make it into the next, if not current, generation's vernacular. It's going to be unbearable.
The one I hate the most is, “And this is what most people miss:”
Re: Various LLM Smells
#286- “(The) honest caveat:” (or “genuine caveat:”, both with the colon) - “(The) honest answer:” (again, with colon) - “The thing to internalize:” - “The smoking gun:” (really, sentences that start with “The :” are a strong tell, but those four are the most prolific) - “load bearing” (when not talking about architecture) - “blast radius” (when not talking about actual explosives, but rather the effect of an event/action…
I routinely use "load bearing" in conversations and writing, both seriously and ironically (like a "load bearing just" or "load bearing paint").. maybe I should stop.
Where did you pick that up from?
Re: Various LLM Smells
#287> The LLM generated writing obviously felt significantly better than my own writing. A general pattern for LLMs is that they look really good at things you are bad at. What that means is that if you find yourself thinking of its output as significantly better than yours in a particular domain, there's a high chance that you are not equipped to judge that quality effectively.
> A general pattern for LLMs is that they look really good at things you are bad at. This is true for coding, too, which I think, to a large degree, might explain the polarized differences in opinions on HN about the quality of LLM-produced code. You have the 1. "AI produces code better than I could possibly write, one shots things it would take me days to do, and has made me 10X more productive!" camp, and you have…
I came up with an analogy the other day -
The 'camp 1' people in the pre-LLM days were probably the ones that often just copy+pasted code from SO they didn't really understand, but since the code seemed to work when they ran it, they thought it was all fine and continued on.
Whereas the 'camp 2' people when trying to find an answer to something, discarded 99% of SO and other similar answers, having the knowledge to see how they had broken edge cases, were limited in some way, didn't actually solve the underlying problem, etc.
Nowadays, 'camp 1' people just use the LLM output and it "seems to work" and consider it all fine. Whereas the 'camp 2' people still continuously see all the faults with it.
Re: Various LLM Smells
#288Earlier quoted context omitted.
> I can't fathom thinking that LLM writing is even remotely passable. People that think this should honestly read more. This makes me think you're only exposing yourself to high quality writing online and from an intelligent circle of friends and coworkers. The average person's reading and writing abilities are _atrocious_ and only getting worse. We're almost at the point where kids are communicating through abbrevia…
...or read. At least in the USA: 21% of adults in the US are illiterate in 2024. 54% of adults have a literacy below a 6th-grade level [1]. 1: https://www.thenationalliteracyinstitute.com/2024-2025-liter...
In an international comparisons, USA comes out somewhere in the middled of developed countries - as it always did. And the differences between countries are not that large.
54% of adults have a literacy below a 6th-grade level is simply not a some kind of catastrophe and it does not mean those people cant read. There is this idea that 6th-grade level is almost like not knowing how to read, but that is simply not the case at all.
Re: Various LLM Smells
#289Earlier quoted context omitted.
Alan Turing poisoned the context in ways we can't comprehend and all LLMs are bound by his dead hand.
wat
Joking that Turing superhumanly foresaw AGI and created the Turing Test as a bar we must never cross, subtly introducing changes to the world's training data to ensure that models could never impersonate humans.
Re: Various LLM Smells
#290One Python one I hate is that it adds crazy amounts of newlines for no real readability gains. Instead of this: def add_three_ints(x: int, y: int, z: int) -> int: return x + y + z it will write: def add_three_ints( x: int, y: int, x: int, ): return x + y + z While it's always preferable to do this when you get either long or complex function signatures, Opus 4.7 and GPT 5.5 do this everywhere. When you combine it wit…
A code formatter like Black can handle that. It's there to enforce a single code style no matter what the contributors use, whether they are human or AI.
Black's default, which I like, has it keep any vertical spacing of comma separated things like function arguments or list contents if they end with a trailing comma. I'm not sure there's an easy way to make a "don't break up short function signatures" rule, but would love to hear if anyone's done anything like that.