Various LLM Smells
shvbsle.in
Various LLM Smells
1–10 of 312 posts
Re: Various LLM Smells
#2 No ___, no ____. Just _____
Re: Various LLM Smells
#3All of those are included in the bulk of the documents passing my work input these days. It is infuriating. Out of principle I maintain 100% me in all my writing but I don't know if it matters. Well maybe it does... an interviewee recently complimented me on the "nicest and most human resume" they saw recently. That felt good
Re: Various LLM Smells
#4KPI cards,
purple gradients
Re: Various LLM Smells
#5> The "JetBrains Mono" font
Thought for sure we'd get a critique of Inter overuse. JetBrains Mono is a lovely font, though.
Re: Various LLM Smells
#6It'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 "contract" or an "artifact" (clearly trained on like three decades of Java lol), everything is constantly "backwards-compatible" or "versioned" (even if working on a brand new greenfield project), and a few others.
Re: Various LLM Smells
#7Those cards, so familiar! Exactly what Opus produced for me.
Did Anthropic and/or OpenAI deliberately train their models to produce websites with a specific design language, or did these stylistic preferences emerge naturally as some kind of LLM-selected optimum?
Re: Various LLM Smells
#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.
Re: Various LLM Smells
#9It'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…
If claude says "load bearing" once more, I think I'll vomit.
Re: Various LLM Smells
#10> 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.
Mnemonic: geLL-Mann amnesia effect