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

Shall I implement it? No

gist.github.com

Post reply on HN
Print view View original

51–60 of 603 posts

Re: Shall I implement it? No

#51

Post by computomatic »

siva7 wrote: post #30
reconnecting wrote: post #24

I’m not an active LLMs user, but I was in a situation where I asked Claude several times not to implement a feature, and that kept doing it anyway.

people read a bit more about transformer architecture to understand better why telling what not to do is a bad idea

I find myself wondering about this though. Because, yes, what you say is true. Transformer architecture isn’t likely to handle negations particularly well. And we saw this plain as day in early versions of ChatGPT, for example. But then all the big players pretty much “fixed” negations and I have no idea how. So is it still accurate to say that understanding the transformer architecture is particularly informative about modern capabilities?

Re: Shall I implement it? No

#53

Post by golem14 »

Obligatory red dwarf quote:

TOASTER: Howdy doodly do! How's it going? I'm Talkie -- Talkie Toaster, your chirpy breakfast companion. Talkie's the name, toasting's the game. Anyone like any toast?

LISTER: Look, _I_ don't want any toast, and _he_ (indicating KRYTEN) doesn't want any toast. In fact, no one around here wants any toast. Not now, not ever. NO TOAST.

TOASTER: How 'bout a muffin?

LISTER: OR muffins! OR muffins! We don't LIKE muffins around here! We want no muffins, no toast, no teacakes, no buns, baps, baguettes or bagels, no croissants, no crumpets, no pancakes, no potato cakes and no hot-cross buns and DEFINITELY no smegging flapjacks!

TOASTER: Aah, so you're a waffle man!

LISTER: (to KRYTEN) See? You see what he's like? He winds me up, man. There's no reasoning with him.

KRYTEN: If you'll allow me, Sir, as one mechanical to another. He'll understand me. (Addressing the TOASTER as one would address an errant child) Now. Now, you listen here. You will not offer ANY grilled bread products to ANY member of the crew. If you do, you will be on the receiving end of a very large polo mallet.

TOASTER: Can I ask just one question?

KRYTEN: Of course.

TOASTER: Would anyone like any toast?

Re: Shall I implement it? No

#54

Post by reconnecting »

oytis wrote: post #28
reconnecting wrote: post #24

I’m not an active LLMs user, but I was in a situation where I asked Claude several times not to implement a feature, and that kept doing it anyway.

Sounds like elephant problem

Elephant in the room problem: this thing is unreliable, but most engineers seem to ignore this fact by covering mistakes in larger PRs.

Re: Shall I implement it? No

#56

Post by layer8 »

kfarr wrote: post #42

What else is an LLM supposed to do with this prompt? If you don’t want something done, why are you calling it? It’d be like calling an intern and saying you don’t want anything. Then why’d you call? The harness should allow you to deny changes, but the LLM has clearly been tuned for taking action for a request.

Why does it ask a yes-no question if it isn’t prepared to take “no” as an answer?

(Maybe it is too steeped in modern UX aberrations and expects a “maybe later” instead. /s)

Re: Shall I implement it? No

#57

Post by miltonlost »

kfarr wrote: post #42

What else is an LLM supposed to do with this prompt? If you don’t want something done, why are you calling it? It’d be like calling an intern and saying you don’t want anything. Then why’d you call? The harness should allow you to deny changes, but the LLM has clearly been tuned for taking action for a request.

Seems like LLMs are fundamentally flawed as production-worthy technologies if they, when given direct orders to not do something, do the thing

Re: Shall I implement it? No

#60

Post by GuinansEyebrows »

kfarr wrote: post #42

What else is an LLM supposed to do with this prompt? If you don’t want something done, why are you calling it? It’d be like calling an intern and saying you don’t want anything. Then why’d you call? The harness should allow you to deny changes, but the LLM has clearly been tuned for taking action for a request.

for the same reason `terraform apply` asks for confirmation before running - states can conceivably change without your knowledge between planning and execution. maybe this is less likely working with Claude by yourself but never say never... clearly, not all behavior is expected :)
Post reply on HN