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

"Don't You Just Upload It to ChatGPT?"

correresmidestino.com

Post reply on HN
Print view View original

231–240 of 408 posts

Re: "Don't You Just Upload It to ChatGPT?"

#231

Post by stogot »

pvillano wrote: post #212
hyperpape wrote: post #200

Earlier quoted context omitted.

First sentence: > In my Ottawa life, every Tuesday evening, I take two gym classes back to back—boxing and the pompously named “body sculpt,” which makes me discover muscles I didn’t know I had. The em-dash matches how you'd speak out loud. You'd say "I take two classes every Tuesday back to back, boxing and 'body sculpt'. Weird name." (Parts of that sentence did flow oddly, but not because of the em-dash). Grammaria…

When I write like I talk, I use a lot of commas. Replacing some of my commas with em dashies, so long as it was done judiciously, would probably make things easier to chunk.

I’ve seen people use colons where em dashes are effective. I use em dashes. AI leans heavily on them for same reason

Re: "Don't You Just Upload It to ChatGPT?"

#234

Post by d_runs_far »

As a public service employee within the GOC, I feel the pain expressed by the author. I sat through a meeting today where somebody with no domain knowledge puffed up their chest to show off their gpt created master lesson plan for a four year long internal training plan that is being re-worked.

I could feel the heads of those around the table that had been teaching this material for a decade starting to explode as this was exactly what others in the thread have described: it looked good until vetted by experts, then it was easy to poke holes as it was just not right

The problem in the public service is that the experts who can review the output are leaving or being nudged out.

Re: "Don't You Just Upload It to ChatGPT?"

#235

Post by mcmcmc »

hyperpape wrote: post #200
Drupon wrote: post #14

An honest to god article full of em dashes that's not because it was AI but because it was a human using them as a crutch to get around crafting sentences that flow naturally. Almost brings a tear to my eye.

First sentence: > In my Ottawa life, every Tuesday evening, I take two gym classes back to back—boxing and the pompously named “body sculpt,” which makes me discover muscles I didn’t know I had. The em-dash matches how you'd speak out loud. You'd say "I take two classes every Tuesday back to back, boxing and 'body sculpt'. Weird name." (Parts of that sentence did flow oddly, but not because of the em-dash). Grammaria…

If I had a nickel for every em-dash I saw that could’ve been a colon…

Re: "Don't You Just Upload It to ChatGPT?"

#236

Post by 627467 »

I'm gonna sound a bit like the clueless gym hr lady: I assume most income generating translation jobs are either mandated by law or commercially high stakes enough to warrant a human to do, no? Were people really being paid to do the type off _low stakes_ translations implied that a automated system can replace?

Maybe a publisher will replace the translator of the next Dan Brown best seller with Mythos? Who cares other than those buying it, getting money out of it?

Re: "Don't You Just Upload It to ChatGPT?"

#237

Post by mcmcmc »

stogot wrote: post #231
pvillano wrote: post #212

Earlier quoted context omitted.

When I write like I talk, I use a lot of commas. Replacing some of my commas with em dashies, so long as it was done judiciously, would probably make things easier to chunk.

I’ve seen people use colons where em dashes are effective. I use em dashes. AI leans heavily on them for same reason

It’s become the exclamation mark of mid-sentence punctuation. It connotes fragmented or interrupted speech in my opinion. The problem is that writing is not speech, that’s why it is more often seen in written dialogue.

Re: "Don't You Just Upload It to ChatGPT?"

#239

Post by jaggederest »

balefulboy wrote: post #201
jaggederest wrote: post #182

Earlier quoted context omitted.

Fable has really spooked me, honestly. It's another big jump, but not in the actual coding. I was pretty comfortable with the "you do the implementation, I do the meta work and steering", and ... no steering required, no meta work required. Here's the backlog, let me know when it's complete, I guess I'm going to go touch grass until I have to review and refine... probably tomorrow? Reminds me of the first time I saw…

Greentext is eh. Very formulaic, in fact very similar to the bottomless pit one, which I'd argue is better because of it's absurdity. I have to ask, did you mention the older GPT version to fable in the prompt?

Of course I did! Wouldn't be faithfully mediocre without the right context

Re: "Don't You Just Upload It to ChatGPT?"

#240

Post by pianopatrick »

throw-the-towel wrote: post #199
Aurornis wrote: post #118

Earlier quoted context omitted.

> This is why I use AI for all my medical questions and doctors use AI to write software, and we both smirk at the quality the other person is getting from it. There is an interesting third group emerging: People who acknowledge the quality problem, but think they can deal with it by applying more AI to the output. This takes the form of people who spin up a lot of "agents" and give them personalities like security d…

> People who acknowledge the quality problem, but think they can deal with it by applying more AI to the output. Brute Force: if it doesn't work, you're just not using enough. What if they're right though?

There are other places where some process has an error rate and you make up for that error rate by doing the work more than once and then comparing results. For example, I've heard in a video that satellites and other space craft often have 3 or 4 processors and compare the results to make sure there were no errors due to radiation. Similarly, we have RAID arrays that store data multiple times because disks can fail. So, even if AI has a failure rate of like 20%, maybe you can make up for that by running the same prompt multiple times with slight variations or with different models, comparing the results and choosing the best.
Post reply on HN