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

ChatGPT Atlas

chatgpt.com

Post reply on HN
Print view View original

491–500 of 768 posts

Re: ChatGPT Atlas

#491

Post by mtillman »

serbuvlad wrote: post #483
sheepscreek wrote: post #475

Earlier quoted context omitted.

There was a phase when ChatGPT would respond to everything I said, even in the same request with something like “..here’s the thing that you asked for, of course, without the fluff.” Or blah blah blah “straight to the point.” Or some such thinly veiled euphemisms. No matter how many times I told it not to talk like that, it didn’t work until I found that “core memory”.

ChatGPT gets about 2-3x as smart the second you turn off memories.

That’s funny. Your phrasing reminds me of a Zappa line “dumb all over and a little ugly on the side”.

Re: ChatGPT Atlas

#492

Post by ahdada8 »

gnarlouse wrote: post #488

I'm still shocked that there isn't basic functionality in chatgpt that allows you to fork conversations to have subtopical conversational threads off of a main one. For example, I'm asking deep philosophical questions, or maybe reaching for a STEM concept slightly beyond my understanding, and that inevitably requires me to ask subquestions (eg "okay wait, what are Conformal Fields?"). Doing so still forces me to do a…

There is! If you click on the three dots menu of a response, there is a “Branch in new chat” option.

I just discovered it today and feel like it’s new.

Re: ChatGPT Atlas

#493

Post by nsonha »

behnamoh wrote: post #25

Anyone feel like OpenAI is acting like Google lately? They announce a lot of products/features and then kill them when they realize people don't use them[0]. They also announce products way before they're ready for launch, just like google[1]. - GPT Plugins? (HN went crazy over this, they called it the "app store moment"...) - GPTs?! - Schedules? - Operator? - The original "codex" model? [0]: I know, the diff is that…

Plugins is the only thing that flopped though. What do you mean by "GPTs?!". Schedules are useful, Operator could be the next version of Atlas.

Re: ChatGPT Atlas

#494

Post by axiom92 »

gnarlouse wrote: post #488

I'm still shocked that there isn't basic functionality in chatgpt that allows you to fork conversations to have subtopical conversational threads off of a main one. For example, I'm asking deep philosophical questions, or maybe reaching for a STEM concept slightly beyond my understanding, and that inevitably requires me to ask subquestions (eg "okay wait, what are Conformal Fields?"). Doing so still forces me to do a…

You can do this at grok.com.

There is a "start thread" option below every conversation. You can also read the responses aloud (helpful if you want to do something async).

Re: ChatGPT Atlas

#495

Post by nsonha »

specproc wrote: post #70
behnamoh wrote: post #25

Anyone feel like OpenAI is acting like Google lately? They announce a lot of products/features and then kill them when they realize people don't use them[0]. They also announce products way before they're ready for launch, just like google[1]. - GPT Plugins? (HN went crazy over this, they called it the "app store moment"...) - GPTs?! - Schedules? - Operator? - The original "codex" model? [0]: I know, the diff is that…

I don't think they've done much that's that impressive since the launch. Cancelled my sub ages ago for other offerings. Zero moat with crazy amounts of debt and financial engineering. What could possibly go wrong?

"OpenAI has zero moat in LLMs"

Re: ChatGPT Atlas

#496

Post by ecommerceguy »

oezi wrote: post #325
mentalgear wrote: post #6

So openAI's answer to Perplexity's Comet. I'm afraid this will be the future, as these AI-browsers do truly bring value. But they open up the gate for a single Big Tech Winner that truly knows everything about you, and can even control everything on your behalf. I really hope open-source Browsers like Firefox follow up soon with better alternatives, like on-device LLMs to counteract the "all in the cloud" LLM approac…

We have to ask when is Chrome bringing this functionality? With Gemini

I'm on Macos and Chrome has a Gemini button that functions very similar to Grox on X.. It's useful and unobtrusive.

I also use Comet for specific financial research, also very useful.

I have edge with Copilot. Never use it. Microsoft is gross.

I have an invite to something called Strawberry but at this point, I'm tapped out. Sorry OpenAI, you're late to the game for me.

Maybe next week.

Re: ChatGPT Atlas

#498

Post by antegamisou »

gnarlouse wrote: post #488

I'm still shocked that there isn't basic functionality in chatgpt that allows you to fork conversations to have subtopical conversational threads off of a main one. For example, I'm asking deep philosophical questions, or maybe reaching for a STEM concept slightly beyond my understanding, and that inevitably requires me to ask subquestions (eg "okay wait, what are Conformal Fields?"). Doing so still forces me to do a…

Doing so still forces me to do a linear conversational format, and it just isn't functional.

So A"I" isn't I... huh, who would've thought.

Re: ChatGPT Atlas

#499

Post by NikolaNovak »

sheepscreek wrote: post #475
ghostpepper wrote: post #454

Earlier quoted context omitted.

I turned off chatGPT memory entirely because it doesn't know how to segment itself. I was getting inane comments like this when asking about winter tires: Because you work in firmware (so presumably you appreciate measurement, risk, durability) you might be more critical of the “wear sooner than ideal” signals and want a tire with more robustness.

There was a phase when ChatGPT would respond to everything I said, even in the same request with something like “..here’s the thing that you asked for, of course, without the fluff.” Or blah blah blah “straight to the point.” Or some such thinly veiled euphemisms. No matter how many times I told it not to talk like that, it didn’t work until I found that “core memory”.

Interesting, that's been driving me absolutely bananas, especially in the voice chat where it takes up like 60% of the response. What kind of core memory did you turn off and how did you find it?

Re: ChatGPT Atlas

#500

Post by baby »

parthdesai wrote: post #364
baby wrote: post #96

Earlier quoted context omitted.

Downloaded Comet last week and I was wondering why anthropic/openAI didn't have one. It's a no brainer. Google's hegemony is really going to take a hit, wondering if hardware-software monopolies like Apple are also going to get hit at some point.

> It's a no brainer. Google's hegemony is really going to take a hit Wonder which company has the best in class browser today, along with a really really good model, an in-house chip, datacenter infra, and most importantly, is cash flow positive?

You really think chrome has such a big moat?
Post reply on HN