[raincole]

My prediction for the top comments of this thread (paraphrased)

1. It's just Microsoft's advertisement

2. No it's just a very effective pattern matching algorithm

3. Please define intelligence first otherwise it's nonsense

4. I welcome our machine overlord

5. Lmao I asked it to do $thing and it failed

I'd like to know if GPT-4 can predict the top comments of this thread?

[BillyTheKing]

from gpt4

write a critical hackernews thread response (not long, maybe like 100 words) for a thread with the following headline

Microsoft Research: GPT-4 exhibits “sparks of general intelligence”

While it's certainly intriguing to hear Microsoft Research claim that GPT-4 exhibits "sparks of general intelligence," I remain skeptical. We must remember that these language models are primarily built on pattern recognition and extensive training data. Even if GPT-4 seems to provide more advanced responses, it's still ultimately constrained by the data it was trained on. In my opinion, we shouldn't mistake this impressive mimicry of human-like behavior for genuine intelligence. Rather, we should focus on creating truly innovative AI systems that can learn, reason, and adapt like humans.

sounds about right!

[atleastoptimal]

Enters rousing speech territory near the end

[cowl]

So you predict the top comments For a claim would be:

1. Dismisal

2. Trivialism

3. Non Well Formed Claim

4. I accept the claim

5. Disprove by counter example

Are you sure you have not forgotten any tactic of debate to include in you prediction?

I predict that you Prediction will result probably in these actions:

1. upvoted

2. downvoted

[IanCal]

6. Discussion around the idea that adds something of value.

[cowl]

Every one of them adds value. Question the premises (wellformed question) Question the motives/importance (dismisal) Disprove by counter example

The only one that can be questioned if it adds something of value is the acceptance and surrender one (I welcome the overlords) although in some forms of thought, advising t0 not fight with the inevitable can be viewed as constructive.

[HopenHeyHi]

6. Meta comment for karma whoring

7. Like 6, but funnier

A. Joke thread pile on

B. Reprimands from humorless

C. Dejected mods having to clean it all up

[voisin]

> B. Reprimands from humorless

You nailed it with this. I’ve never given it enough attention but this is totally bang on, found is a huge portion of highly commented posts.

[HopenHeyHi]

These things ebb and flow my dear Adso: https://www.youtube.com/watch?v=jUUB96c6EpY

[super256]

Your unedited comment was funnier

[moi2388]

I thoroughly enjoyed point 7.

[jwdunne]

Hang on, let me cover B:

tHiS sHoUlDn’T bE oN hAcKeRnEws

[narrator]

8. Offensive, but true comment that gets a bunch of upvotes and then gets flagged.

[minihat]

"Did you know that squirrels can purr like cats? GPT-4 might be intelligent, but can it teach a squirrel to code?"

I asked gpt-4 for a comment no hn user would ever make on this article. Now you need a category for stubbornly original comments determined not to be numbered.

[TheHappyOddish]

What about "guys, it's just a fancy markov chain"?

[thunderbong]

No "I could probably do this over a weekend"?

[reidjs]

As a poster of one of those bullet points, I feel personally attacked