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

ai;dr

0xsid.com

Post reply on HN
Print view View original

251–260 of 313 posts

Re: ai;dr

#251

Post by latexr »

parsimo2010 wrote: post #238
wrs wrote: post #88

Earlier quoted context omitted.

If you’re judging my writing so shallowly, I don’t think I’m writing for you.

I don’t think I’m judging shallowly- there is no em-dash on a standard keyboard. The one way it ends up in real writing is if you use a typesetting program like LaTeX, or Word changes an en-dash with auto formatting, or the user consciously interrupts their writing flow to insert the character with a special keystroke combination or by pasting it in. The proportion of people who do any of those things in writing for…

> there is no em-dash on a standard keyboard. The one way it ends up in real writing is (…)

Then you proceed to list multiple ways to do it, but neglected to mention that by default on Apple operating systems they are inserted automatically when typing “--“. It’s something you have to explicitly turn off of you don’t want it. On Apple mobile operating systems you can also long press the hyphen to get the option. Em-dashes are trivial to type.

Re: ai;dr

#252

Post by ziml77 »

adwf wrote: post #226
gordonhart wrote: post #153

Earlier quoted context omitted.

The main coding agent failure modes I've seen: - Proliferation of utils/helpers when there are already ones defined in the codebase. Particularly a problem for larger codebases - Tests with bad mocks and bail-outs due to missing things in the agent's runtime environment ("I see that X isn't available, let me just stub around that...") - Overly defensive off-happy-path handling, returning null or the semantic "empty"…

Oh god, the bad mocks are the worst. Try adding instructions not to make mocks and it creates "placeholders", ask it to not create mocks or placeholders and it creates "stubs". Drives me mad... To add to this list: - Duplicate functions when you've asked for a slight change of functionality (eg. write_to_database and write_to_database_with_cache), never actually updating all the calls to the old function so you have…

I'm sort of happy to see all these things I run into listed out as issues people have so I know it's not just me experiencing and being bothered by these behaviors.

Re: ai;dr

#253

Post by kimixa »

nxobject wrote: post #144
ssiddharth wrote: post #50

Earlier quoted context omitted.

My biggest sorrow right now is the fact that my beloved emdash is a major signal for AI generated content. I've been using it for decades now but these days, I almost always pause for a second.

What I do – and I know this isn't conventional style – is use ex dashes. (Or, you could use spaces between em dashes, as incorrect as it is.)

> Or, you could use spaces between em dashes, as incorrect as it is.

That's the normal way of using them in British English. Though they also tend to be the (slightly shorter) en-dashes too.

I feel that style is often pretty common on the "old" internet - possibly related to how they can be so easily be replaced by a hyphen back when ascii was a likely limitation.

Re: ai;dr

#254

Post by manuelmoreale »

akoboldfrying wrote: post #231
manuelmoreale wrote: post #175

Earlier quoted context omitted.

> I've been using it for decades now but these days, I almost always pause for a second. Wrote about this before [0] but my 2c: you shouldn't pause and you should keep using them because fuck these companies and their AI tools. We should not give them the power to dictate how we write. [0]: https://manuelmoreale.com/thoughts/on-em-dashes

That's not really how it works. Gemini tells me that for thousands of years, the swastika was used as "a symbol of positivity, luck and cosmic order". Try drawing it on something now and showing it to people. Is this an effective way to fight Nazism? I think it's brave to keep using em dashes, but I don't think it's smart, because we human writers who like using them (myself very much included) will never have the mi…

> Gemini tells me that for thousands of years, the swastika was used as "a symbol of positivity, luck and cosmic order". Try drawing it on something now and showing it to people. Is this an effective way to fight Nazism?

I'm happy to change my position when some 13 million people are killed by lunatics that used the em dash as the symbol of their ideology. Until then, I'll keep using it everywhere it's appropriate.

Also, if we don't have the guts to resist even when the stakes are this low and the consequences for our resistance are basically non existent, then society is doomed. We might as well roll on our side and die.

> At least, not until the dominant forces in AI decide of their own accord that they don't want their LLMs emitting so many of them.

It's not a power I'm willing to give them. What if tomorrow they tweak something and those tool start to use a specific word more often? Or a different punctuation sign? What do we do then? Do we constantly adapt, playing whack-a-mole? What if AI starts asking a lot more questions in their writing? Do we stop asking them as a result?

You feel free to adapt and bend. I'm personally not going to do it and if someone starts thinking that I'm using AI to write my thoughts and as a result that's on them.

Re: ai;dr

#255

Post by copperx »

bananaflag wrote: post #224
ginsider_oaks wrote: post #155

Earlier quoted context omitted.

> Programs must be written for people to read, and only incidentally for machines to execute. from the preface of SICP.

Well SICP was already considered here to be obsolete with the rise of the library-abstraction culture.

And AI is great at performing basic science on libraries.

Re: ai;dr

#256

Post by ggggffggggg »

latexr wrote: post #251
parsimo2010 wrote: post #238

Earlier quoted context omitted.

I don’t think I’m judging shallowly- there is no em-dash on a standard keyboard. The one way it ends up in real writing is if you use a typesetting program like LaTeX, or Word changes an en-dash with auto formatting, or the user consciously interrupts their writing flow to insert the character with a special keystroke combination or by pasting it in. The proportion of people who do any of those things in writing for…

> there is no em-dash on a standard keyboard. The one way it ends up in real writing is (…) Then you proceed to list multiple ways to do it, but neglected to mention that by default on Apple operating systems they are inserted automatically when typing “--“. It’s something you have to explicitly turn off of you don’t want it. On Apple mobile operating systems you can also long press the hyphen to get the option. Em-d…

To be fair, if they don’t know that they probably run Android, and are you even writing for them?

I bet their bubbles are… green. The horror!

Re: ai;dr

#257

Post by vonunov »

Yizahi wrote: post #190
deron12 wrote: post #141

Earlier quoted context omitted.

AI never uses em dashes in a pair like this, whereas most people who like em dashes do. Anyone who calls paired em dash writing AI is only revealing themselves to be a duffer.

In my limited text generation experience, LLMs use em-dashes precisely like that, only without spaces on the sides and always in pairs in a single sentence. Here some examples from my Gemini history: "The colors we see—like blue, green, and hazel—are the result of Tyndall scattering." "Several interlocking cognitive biases create a "safety net" around the familiar, making the unknown—even if objectively better—feel l…

Yes, the LLMs have made great progress in that regard. It wasn't too long ago that the majority of dashes seen in LLM material could have been commas, periods, or nothing at all with no loss of tone or meaning, and almost none were used to offset parenthetical phrases. It was nearly exclusively an overdramatic flourish. And now look at them. They're growing up. Just makes you want to squeeze them until they pop.

Re: ai;dr

#258

Post by vonunov »

catoc wrote: post #78
ssiddharth wrote: post #50

Earlier quoted context omitted.

My biggest sorrow right now is the fact that my beloved emdash is a major signal for AI generated content. I've been using it for decades now but these days, I almost always pause for a second.

Exactly this! I love(d) using em dashes. Now they’ve become ehm dashes, experiencing exactly that pause — that moment of hesitation — that you describe

Embrace the double hyphen -- it's still attested in Garner's ;)

Re: ai;dr

#259

Post by vonunov »

nxobject wrote: post #144
ssiddharth wrote: post #50

Earlier quoted context omitted.

My biggest sorrow right now is the fact that my beloved emdash is a major signal for AI generated content. I've been using it for decades now but these days, I almost always pause for a second.

What I do – and I know this isn't conventional style – is use ex dashes. (Or, you could use spaces between em dashes, as incorrect as it is.)

Chicago says to format dashes like this—and ellipses . . . like this. . . .

AP says to format dashes like this — and ellipses ... like this. ...

Who's "correct"?

Re: ai;dr

#260

Post by gloflo »

hinkley wrote: post #132
ravirajx7 wrote: post #93

AI has kind of ruined internet for me. I no longer feel joy in reading things as almost most of the writing seem same and pale to me as if everyone is putting thoughts in the same way. Having your own way of writing always felt personal in which you expressed your feelings most of the time. The most sad part for me is I no longer am able to understand someone's true feelings (which anyway was hard to express in writi…

I used to daydream of a 'dark web' but for humans not criminals. But at this point I don't know how you'd keep slop out, given how high human collusion has gotten of late.

You'd need a trusted network of community. Web of trust style.
Post reply on HN