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

Various LLM Smells

shvbsle.in

Post reply on HN
Print view View original

261–270 of 312 posts

Re: Various LLM Smells

#261

Post by ninjalanternshk »

yuye wrote: post #200
overgard wrote: post #181

Earlier quoted context omitted.

Yup, pretty much. The hard part too is it's not like you can just learn the basics and be able to tell good code apart from bad -- the more you learn to code, the more intricate your understanding of good code is. It's like becoming a good writer; just knowing grammar and spelling doesn't make your writing interesting. Not to mention that there's just a lot of bad advice out there that you can't recognize as bad advi…

>I think looking at an LLM code and thinking you're now a coder is like watching a someone play guitar and think you can just pick up a guitar and play a song. The truth is, if you want to be good, you have to do the work. So many posts here on HN claiming they created another useful tool with AI. No, you didn't create it. AI did. You only had a supporting role. You're Ringo Starr and the AI is John Lennon.

> No, you didn't create it. AI did.

No, AI assembled bits of code written by hundreds of programmers before you.

Re: Various LLM Smells

#262

Post by ninjalanternshk »

saaaaaam wrote: post #133
Planktonne wrote: post #8

> 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.

I partly write words for a living. Claude is really really bad at writing prose that doesn’t make me want to vomit. I rarely write code, and only once for a living. But I feel like I’m a superhuman and one step away from being a zillionaire when Claude gives me a bunch of code it has written in seconds. I WILL CHANGE THE WORLD!! And then I remember that Claude can’t write words that don’t make me want to break things…

I’ll take “what is Dunning–Kruger” for $200 Alex.

Re: Various LLM Smells

#263

Post by ninjalanternshk »

mjrbrennan wrote: post #209
spdustin wrote: post #18

- “(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…

The funniest one I've seen with regularity is belt-and-suspenders/belt-and-braces, when I've never seen anyone ever use that term. I had to tell AI to stop using it, it was just annoying.

I frequently use “belt-and-suspenders” — probably not in wri… crap I just used an em dash.

Re: Various LLM Smells

#265

Post by ninjalanternshk »

metadat wrote: post #88

Don't forget about Contrastive Negation : > Contrastive negation is a rhetorical structure that denies a specific idea in the first half of a sentence and asserts an alternative in the second half. > It typically follows an "It’s not X, it’s Y" or "not just X, but Y" formula. Wikipedia also has a great resource which covers many of the common LLM patterns: https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing

As someone who’s writing gets flagged as AI a lot, I appreciate the opening disclaimer section.

And I especially appreciate the idea that these patterns aren’t the problem. Don’t just fix the patterns. The problem is they point to hastily or carelessly written content.

Re: Various LLM Smells

#266

Post by renyicircle »

> Humans trust symmetry because it feels like intelligence made visible I hope this one didn't make it into the author's math blog. I don't understand what this means. I don't "trust" symmetry, I never think of symmetry as having to do with "intelligence". How did it even come up with that.

Re: Various LLM Smells

#267

Post by ninjalanternshk »

KronisLV wrote: post #5

> The "JetBrains Mono" font Thought for sure we'd get a critique of Inter overuse. JetBrains Mono is a lovely font, though.

I fear for falling into the trap some political parties get into — anything the other guy came up with is bad, by definition.

If JetBrains Mono suits your work you should use it, not avoid it specifically because AI often uses it.

Re: Various LLM Smells

#268

Post by gchamonlive »

embedding-shape wrote: post #108
gchamonlive wrote: post #23

Earlier quoted context omitted.

It's like a gross looking slice of pizza, it's mindbending because at first it looks good, after all it's pizza, but something in it makes it really disgusting

Maybe we're looking at different pizza slices, but all I see is bread, tomato sauce and cheese, and it all looks delicious.

Yes https://downtownlongbeach.org/wp-content/uploads/Broadway-Pi... but https://i.chzbgr.com/full/10412716544/h06A6A341

And both come from ovens.

Re: Various LLM Smells

#269

Post by sznio »

unshavedyak wrote: post #141
spiffistan wrote: post #138

Earlier quoted context omitted.

These seem mostly like Claudeisms. I feel each model (and even generation) has their own set of these isms.

Which seems logical - if they were somehow consistent between all LLMs i'd be even more curious how LLMs are... crab-evolving to 'isms, but hopefully that's not the case hah. (i say crab-evolving in jest)

I use qwen3.5 locally and it often outputs a lot of claude-isms. Claude actually stopped telling me that I'm absolutely right with every message, but Qwen still does.

I think that the convergence of these tics is just a symptom of distillation.

Re: Various LLM Smells

#270

Post by Sammi »

eapriv wrote: post #239

> 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.

This is a big fat "it depends". It depends on how you use the llm. You can use the llm to write your homework or you can use the llm as a teaching assistant to help you learn. Different people choose different paths.

I grew up seeing this very relevant image on the wall of my grandparents:

https://en.wikipedia.org/wiki/Matthew_7:13#/media/File:Der_b...

Lower quality version with The Eye of Providence not retouced out (the version I remember):

https://commons.wikimedia.org/wiki/File:Der_breite_und_der_s...

Post reply on HN