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

GPT-4o

openai.com

Post reply on HN
Print view View original

501–510 of 1001 posts

Re: GPT-4o

#501

Post by mewpmewp2 »

freediver wrote: post #394

Impressed by the model so far. As far as independent testing goes, it is topping our leaderboard for chess puzzle solving by a wide margin now: https://github.com/kagisearch/llm-chess-puzzles?tab=readme-o...

I see you have Connect 4 test there.

I tried playing against the model, it didn't do well in terms of blocking my win.

However it feels like it might be possible to make it try to think ahead in terms of making sure that all the threats are blocked by prompting well.

Maybe that could lead to somewhere, where it will explain its reasoning first?

This prompt worked for me to get it to block after I put 3 in the 4th column. It otherwise didn't

Let's play connect 4. Before your move, explain your strategy concisely. Explain what you must do to make sure that I don't win in the next step, as well as explain what your best strategy would be. Then finally output the column you wish to drop. There are 7 columns.

Always respond with JSON of the following format:

type Response ={

      am_i_forced_to_block: boolean;

      other_considerations: string[];

      explanation_for_the_move: string;

      column_number: number;
}

I start with 4.

Edit:

So it went

Me: 4

It: 3

Me: 4

It: 3

Me: 4

It: 4 - Successful block

Me: 5

It: 3

Me: 6 - Intentionally, to see if it will win by putting another 3.

It: 2 -- So here it failed, I will try to tweak the prompt to add more instructions.

me: 4

Re: GPT-4o

#502

Post by elicksaur »

freediver wrote: post #394

Impressed by the model so far. As far as independent testing goes, it is topping our leaderboard for chess puzzle solving by a wide margin now: https://github.com/kagisearch/llm-chess-puzzles?tab=readme-o...

> and Kagi is well positioned to serve this need.

>CEO & founder of Kagi

Important context for anyone like me who was wondering where the boldness of the first statement was coming from.

Edit: looks like the parent has been edited to remove the claim I was responding to.

Re: GPT-4o

#503

Post by rubidium »

CooCooCaCha wrote: post #467
mellosouls wrote: post #69

Very, very impressive for a "minor" release demo. The capabilities here would look shockingly advanced just 5 years ago. Universal translator, pair programmer, completely human sounding voice assistant and all in real time. Scifi tropes made real. But: Interesting next to see how it actually performs IRL latency and without cherry-picking. No snark, it was great but need to see real world power. Also what the benefit…

My guess is they're banking on the free version being rate limited and people finding it so useful that they want to remove the limit. Like giving a new user a discount on heroin. At least that's the strategy that would make most sense to me.

I have the paid version and it’s not connecting

Re: GPT-4o

#505

Post by glonq »

avi_vallarapu wrote: post #457

Someone said GPT-4o can replace a Tutor or a Teacher in Schools. Well, that's way too far.

Tell me that you've enjoyed good teachers and good schools without telling me that you had good teachers in good schools ;)

Re: GPT-4o

#506

Post by titzer »

Can't wait for this AI voice assistant to tell me in a sultry voice how I should stay in an AirBnB about 12 times a day.

Re: GPT-4o

#507

Post by dkarras »

lxgr wrote: post #62

Will this include image generation for the free tier as well? That's a big missing feature in OpenAI's free tier compared to Google and Meta.

is oai image generation any different than the microsoft copilot provides for free? I thought they were the same.

Re: GPT-4o

#508

Post by jimkleiber »

I worry that this tech will amplify the cultural values we have of "good" and "bad" emotions way more than the default restrictions that social media platforms put on the emoji reactions (e.g., can't be angry on LinkedIn).

I worry that the AI will not express anger, not express sadness, not express frustration, not express uncertainty, and many other emotions that the culture of the fine-tuners might believe are "bad" emotions and that we may express a more and more narrow range of emotions going forward.

Almost like it might become an AI "yes man."

Re: GPT-4o

#509

Post by dkarras »

sebastiennight wrote: post #82

Anyone who watched the OpenAI livestream: did they "paste" the code after hitting CTRL+C ? Or did the desktop app just read from the clipboard? Edit: I'm asking because of the obvious data security implications of having your desktop app read from the clipboard _in the live demo_... That would definitely put a damper to my fanboyish enthusiasm about that desktop app.

macOS asks you to give permission for an application to read your clipboard. do other operating systems not have that?

Re: GPT-4o

#510

Post by freediver »

elicksaur wrote: post #502
freediver wrote: post #394

Impressed by the model so far. As far as independent testing goes, it is topping our leaderboard for chess puzzle solving by a wide margin now: https://github.com/kagisearch/llm-chess-puzzles?tab=readme-o...

> and Kagi is well positioned to serve this need. >CEO & founder of Kagi Important context for anyone like me who was wondering where the boldness of the first statement was coming from. Edit: looks like the parent has been edited to remove the claim I was responding to.

Yeah, it was an observation that was better suited for a tweet than HN. Here it is:

https://twitter.com/vladquant/status/1790130917849137612

Post reply on HN