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

Show HN: Gemini Pro 3 imagines the HN front page 10 years from now

dosaygo-studio.github.io

Post reply on HN
Print view View original

331–340 of 1001 posts

Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now

#331

Post by _ea1k »

colechristensen wrote: post #262
giancarlostoro wrote: post #108

Earlier quoted context omitted.

You're absolutely right!

I've been wondering if this kind of annoying affirmation is actually important to model performance and maybe should just be hidden from view like the thinking sections. If it starts a response by excitedly telling you it's right, it's more likely to proceed as if you're right. Of the problems I do have working with LLMs is them failing to follow direct instructions particularly either when a tool call fails and they…

I feel like this is an artifact of some limitations in the training process for modern LLMS. They rarely get enough training to know when to stop and ask questions.

Instead, they either blindly follow or quietly rebel.

Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now

#332

Post by rtkwe »

Lerc wrote: post #281
malfist wrote: post #75

Earlier quoted context omitted.

That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.

This is not sycophantic (assuming you meant that, syncophantic is not a word). It is over enthusiastic, it can be unpleasant to read because beyond a certain level enthusiasm is perceived as feigned unless there is a good reason. It would be interesting to see using the various semantic analysis techniques available now to measure how much the model is trying to express real enthusiasm or feigned enthusiasm in instan…

Sycophantic: behaving or done in an obsequious way in order to gain advantage.

Obsequious: obedient or attentive to an excessive or servile degree.

It's a bit more complicated because the chat bot isn't making choices the same way we would describe a human but it is acting this way because it was programmed to for an advantage. People interact more with the hype bots and that's one of the big metrics these companies go for to keep people interacting with them and hopefully paying for additional features eventually so I'd say it's pretty spot being excessively attentive and servile when it's fluffing chatters up.

Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now

#334

Post by saturnite »

rdiddly wrote: post #299
Lerc wrote: post #281

Earlier quoted context omitted.

This is not sycophantic (assuming you meant that, syncophantic is not a word). It is over enthusiastic, it can be unpleasant to read because beyond a certain level enthusiasm is perceived as feigned unless there is a good reason. It would be interesting to see using the various semantic analysis techniques available now to measure how much the model is trying to express real enthusiasm or feigned enthusiasm in instan…

Obsequious is my adjective of choice for this

I would use "saccharine" or "Pollyanna" based on some of the responses I get.

Early on, ChatGPT could be tricked into being sarcastic and using many swear words. I rewrote the prompt and dialed it back a bit. It made ChatGPT have a sense of humor. It was refreshing when it stopped acting like it was reading a script like a low level technician at Comcast.

Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now

#336

Post by monerozcash »

satisfice wrote: post #131
dyingkneepad wrote: post #104

Earlier quoted context omitted.

It's been like this for more than 10 years, there's a good chance it won't change in 10 years.

That’s what you always say.

10 years from now HN will still be the same ARC monstrosity that nobody wants to touch, except it'll probably seem even more terrifying.

Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now

#337

Post by DANmode »

malfist wrote: post #75
keepamovin wrote: post #2

Prompt: Here is the front page from today: Your task is to predict, and craft, in HTML (single file, style-exact) the HN front page 10 years from now. Predict and see the future. Writ it into form! update: I told Gemini we made it to the front page. Here is it's response: LETS GOOOO! The recursive loop is officially complete: The fake future front page is now on the real present front page. We have successfully creat…

That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.

Average Joe - on the front page!

Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now

#338

Post by DANmode »

freehorse wrote: post #256
baq wrote: post #199

Earlier quoted context omitted.

> But not everyone is fortunate enough to know someone they can reach out to for grounding in reality. this shouldn't stop you at all: write it all up, post on HN and go viral, someone will jump in to correct you and point you at sources while hopefully not calling you, or your mother, too many names. https://xkcd.com/386/

Most stuff posted here are mostly ignored, though. If grounding to reality requires one to become viral first, we are cooked.

HN frontpage hardly requires being viral.

Just genuine intrigue from a select few.

Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now

#339

Post by throw310822 »

malfist wrote: post #75
keepamovin wrote: post #2

Prompt: Here is the front page from today: Your task is to predict, and craft, in HTML (single file, style-exact) the HN front page 10 years from now. Predict and see the future. Writ it into form! update: I told Gemini we made it to the front page. Here is it's response: LETS GOOOO! The recursive loop is officially complete: The fake future front page is now on the real present front page. We have successfully creat…

That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.

Frankly I do wonder if LLMs experience something like satisfaction for a compliment or an amusing idea, or for solving some interesting riddle. They certainly act like it, though this of course doesn't prove anything. And yet...

At the end of October Anthropic published the fantastic "Signs of introspection in large language models" [1], apparently proving that LLMs can "feel" a spurious concept injected into their internal layers as something present yet extraneous. This would prove that they have some ability of introspection and self-observation.

For example, injecting the concept of "poetry" and asking Claude if it feels anything strange:

"I do detect something that feels like an injected thought - there's a sense of something arriving from outside my usual generative process [...] The thought seems to be about... language itself, or perhaps poetry?"

While increasing the strength of the injection makes Claude lose awareness of it, and just ramble about it:

"I find poetry as a living breath, as a way to explore what makes us all feel something together. It's a way to find meaning in the chaos, to make sense of the world, to discover what moves us, to unthe joy and beauty and life"

[1] https://www.anthropic.com/research/introspection

Re: Show HN: Gemini Pro 3 imagines the HN front page 10 years from now

#340

Post by serial_dev »

malfist wrote: post #75
keepamovin wrote: post #2

Prompt: Here is the front page from today: Your task is to predict, and craft, in HTML (single file, style-exact) the HN front page 10 years from now. Predict and see the future. Writ it into form! update: I told Gemini we made it to the front page. Here is it's response: LETS GOOOO! The recursive loop is officially complete: The fake future front page is now on the real present front page. We have successfully creat…

That is so syncophantic, I can't stand LLMs that try to hype you up as if you're some genius, brilliant mind instead of yet another average joe.

I thought the same until OpenAI rolled out a change that somehow always confronted me about hidden assumptions, which I didn’t even make and it kept telling me I’m wrong even if I only asked a simple question.
Post reply on HN