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

221–230 of 312 posts

Re: Various LLM Smells

#221

Post by chungusamongus »

dvt wrote: post #11
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.

Honestly, I can't fathom thinking that LLM writing is even remotely passable. People that think this should honestly read more. One book a month is hardly an aspirational goal. You don't even have to read Melville or Hemingway or Chaucer or Shakespeare, just pick up any popular NYT best seller, and it'll be significantly better than anything an LLM can generate.

This is just the last domain people can desperately cling to because style is totally subjective.

Re: Various LLM Smells

#222

Post by nottorp »

tptacek wrote: post #50

The LLM writing sameness is bad. Use LLMs to help your writing! But don't include a word they generate, even just a vocabulary adjustment, in your own output. Have them critique structure and flow, spot overused words and passive constructions and dumb picks for topic sentences. It's great for that, and those are all objective improvements in your writing that won't mess up your style. The LLM sameness in web design…

> The LLM sameness in web design is good.

I'd say that sameness isn't good either from a LLM or solo founder SaaS #171876137.

Re: Various LLM Smells

#223

Post by nottorp »

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.

On a tangent, since it's called JetBrains Mono I guess it's JetBrains' IP?

Is it even legal to use it in $RANDOM_WEBSITE?

Re: Various LLM Smells

#224

Post by nottorp »

dvt wrote: post #6

It's kind of interesting how genuinely hard it is to get models to deviate from basically all of these tropes. You can straight up tell it "I hate that card design, do something different, get creative!" and it'll do something either (a) ugly as sin (clearly just essentially a random walk through parameters) or (b) some same-y derivation of that card. In coding, I've noticed a few tropes as well: everything is a "con…

> I hate that card design, do something different, get creative!

It can't get creative, it can only generate based of what's a majority in it's training data.

Re: Various LLM Smells

#225

Post by raincole »

Derbasti wrote: post #215
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…

I wonder, could we use these catch phrases to track down what data was used dor training? They must have occurred in abundance in some training corpus. Perhaps some specific company's email culture?

> They must

Nope. LLMs are RLHF'ed to the brim.

Re: Various LLM Smells

#226

Post by rmellow »

GrinningFool wrote: post #27
n42 wrote: post #2

No ___, no ____. Just _____ or using "honest" to describe an approach.

Jab, jab, thrust is how I think about that pattern. Or tap tap whack, if you prefer. And it shows up for for positives too: "Smooth. Effortless. A perfect fit for your needs". In any style of informal or persuasive writing this shows up , as if it has to drive the point in. I kind of wish we'd stop talking openly about what the tells are. It's nice to be able to determine with fair accuracy - but it couldn't last for…

Ironically, your entire post can be read as such, almost perfectly!

Labeling each sentence (J)ab and (T)hrust, and using colon ":" to indicate arguments, one gets:

```

J: J. J. T.

J: "J. J. T".

T: T.

T: J. J. T.

```

Re: Various LLM Smells

#227

Post by agos »

TacticalCoder wrote: post #60

So the year is 2026 and we cannot point a LLM at, say, this HN thread, and give it the instructions: "I don't want to look like a dumbass, so don't make these obvious mistakes / don't use these obvious tells" !?

This for me is one of the greatest cognitive dissonance moments with LLMs: on one hand we have the proposition “LLMs will do everything, take your job, automate anything that can be automated, produce novel research, lead humankind to a golden age” and other hand we have “no way to make it not sound like a guy who just learned this two sentences”.

Re: Various LLM Smells

#228

Post by Udo_Schmitz »

nottorp wrote: post #223
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.

On a tangent, since it's called JetBrains Mono I guess it's JetBrains' IP? Is it even legal to use it in $RANDOM_WEBSITE?

https://github.com/JetBrains/JetBrainsMono/blob/master/OFL.t...

Re: Various LLM Smells

#229

Post by palmotea »

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. You only had a supporting role. You're Ringo Starr and the AI is John Lennon.

It's even worse than that: you're the Ringo Starr and the AI is a a "John Lennon" who sucks and is boring and uncreative.

Re: Various LLM Smells

#230

Post by palmotea »

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 [utterly mundane thing] was decisive.
Post reply on HN