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

311–320 of 1001 posts

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

#311

Post by golem14 »

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…

Feels exactly the same as the "yes, and" crowd.

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

#313

Post by nromiun »

> Is it time to rewrite sudo in Zig?

Taking the current RIIR movement and casting it on Zig as the next hyped language is clever.

> ITER achieves net positive energy for 20 consecutive minutes

Hilarious. I guess not many people talk about the challenge of proper shielding material against fusion radiation. Otherwise we would get hallucinations about new exotic heavy metals too.

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

#314

Post by edschofield »

radicality wrote: post #124
sallveburrpi wrote: post #100

Earlier quoted context omitted.

You should try my nihilistic Marvin fine-tune - guaranteed to annihilate your positive outlook on life since it’s all meaningless in the end anyway and then you die

Or try the very sarcastic and nihilistic ‘Monday’ gpt, which surprisingly is an official openAI gpt. edit, add link: https://chatgpt.com/g/g-67ec3b4988f8819184c5454e18f5e84b-mon...

Thanks for the link! I didn’t know Monday existed. I laughed so hard at its output. But I fear that using it regularly would poison my soul…

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

#315

Post by unoti »

hereonout2 wrote: post #227
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.

I often try running ideas past chat gpt. It's futile, almost everything is a great idea and possible. I'd love it to tell me I'm a moron from time to time.

> I often try running ideas past chat gpt. It's futile, almost everything is a great idea and possible. I'd love it to tell me I'm a moron from time to time.

Here's how to make it do that. Instead of saying "I had idea X, but someone else was thinking idea Y instead. what do you think" tell it "One of my people had idea X, and another had idea Y. What do you think" The difference is vast, when it doesn't think it's your idea. Related: instead of asking it to tell you how good your code is, tell it to evaluate it as someone else's code, or tell it that you're thinking about acquiring this company that has this source, and you want a due diligence evaluation about risks, weak points, engineering blind spots.

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

#316

Post by mondrian »

barbacoa wrote: post #218
woliveirajr wrote: post #53

Earlier quoted context omitted.

"Ask HN: How do you prevent ad-injection in AR glasses?" Things that I haven't thought but, after seeing it, makes total sense. Scary.

2040 HN: "Ask HN: How do you prevent ad-injection in my brain implant?"

Black Mirror episode: https://en.wikipedia.org/wiki/Common_People_(Black_Mirror)
Post reply on HN