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

Less human AI agents, please

nial.se

Post reply on HN
Print view View original

141–150 of 184 posts

Re: Less human AI agents, please

#141

Post by TZubiri »

js8 wrote: post #12

A very human thing to do is - not to tell us which model has failed like this! They are not all alike, some are, what I observe, order of magnitude better at this kind of stuff than others. I believe how "neurotypical" (for the lack of a better word) you want model to be is a design choice. (But I also believe model traits such as sycophancy, some hallucinations or moral transgressions can be a side effect of trainin…

Also, there's no specific examples of what the prompt was and what the result was. Just a big nothingburger

Re: Less human AI agents, please

#142

Post by cadamsdotcom »

nialse wrote: post #58
cadamsdotcom wrote: post #56

Earlier quoted context omitted.

Make it write a script with dry run and a file name list. You’ll be amazed how good the script is. My agent did 20 class renames and 12 tables. Over 250 files and from prompt to auditing the script to dry run to apply, a total wall clock time of 7 minutes. Took a day to review but it was all perfect!

Asking for code to manipulate the AST is another route. In python it can do absolute magic.

Glad to see others have discovered this! It’s mind boggling - the agent can do sheer wizardry.

Re: Less human AI agents, please

#144

Post by Jtarii »

slopinthebag wrote: post #135
Jtarii wrote: post #132

Earlier quoted context omitted.

When someone asks you a question in what ways are you not an "autocomplete"? You aren't aware of how you come up with the words you are saying, you just start talking and the next word somehow falls out of your mouth. Maybe you think before you start talking, but where do the thoughts come from? They just appear to you in your head. We are just as much a predictive machine as LLMs, the human brain is just fuzzier.

Well, maybe this is how you think but not everyone is a self-admitted NPC. Speak for yourself only please.

Think of a movie.

You had literally -zero- input in what your brain gave you as an answer. It just gave you something, you can make up whatever story you want to tell yourself, "it's my favourite movie", "I saw it last week", whatever you want. It doesn't change the fact that the words on your screen triggered some neural pathway in your brain that is totally out of your control and landed on "Titanic".

Re: Less human AI agents, please

#145

Post by gitaarik »

gregates wrote: post #15

The version of this I encounter literally every day is: I ask my coding agent to do some tedious, extremely well-specified refactor, such as (to give a concrete real life example) changing a commonly used fn to take a locale parameter, because it will soon need to be locale-aware. I am very clear — we are not actually changing any behavior, just the fn signature. In fact, at all call sites, I want it to specify a def…

I have the feeling they do this to save tokens in case you didn't mean to execute such a big task right away. But yeah it's simple enough to say "Just do it now"

Re: Less human AI agents, please

#147

Post by raylad »

I haven’t noticed this sort of behavior with opus 4.6, but the first time I used 4.7 it decided to “simplify“ an existing piece of functionality rather than fixing it, which of course made it completely unusable.

Re: Less human AI agents, please

#148

Post by Jtarii »

chrisjj wrote: post #131
Jtarii wrote: post #129

Earlier quoted context omitted.

You can't understand human behaviour by reading a physics textbook.

Of course not. One of the major differences between intelligent and word-guessing autocomplete.

Do you think you could explain all AI behaviour by reading a physics textbook?

Re: Less human AI agents, please

#149

Post by fenomas »

DangitBobby wrote: post #139
fenomas wrote: post #49

Earlier quoted context omitted.

Nope, "less" is what TFA means.

Actually it's either because less versus fewer is not an actual rule

It's not a grammar issue; only "less" matches TFA's meaning.

(Aside: it's better not to be pedantic, but if you must be pedantic you should remember to be correct as well.)

Re: Less human AI agents, please

#150

Post by DangitBobby »

fenomas wrote: post #149
DangitBobby wrote: post #139

Earlier quoted context omitted.

Actually it's either because less versus fewer is not an actual rule

It's not a grammar issue; only "less" matches TFA's meaning. (Aside: it's better not to be pedantic, but if you must be pedantic you should remember to be correct as well.)

True. People often incorrectly believe that less and fewer have distinct cases where only one word is correct. They are mistaken.
Post reply on HN