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

481–490 of 768 posts

Re: ChatGPT Atlas

#481

Post by StarterPro »

So you'll never need to remember anything. ChatGPT remembers that PH video from 10 months ago AND the improved recipe for your mom's pasta sauce.

In all seriousness: they won't make a dent in the browser market, people still using GPT resources for free, and if they do start ads why would a company work with a company that's already hemorrhaging billions?

If you stop thinking (a tough ask for ai users, I know) about this from a never-ending money perspective and live in the real world, financially and environmentally it's gonna take decades to undo the damage. All for what?

Re: ChatGPT Atlas

#482

Post by seizethecheese »

groby_b wrote: post #295
ascorbic wrote: post #285

Earlier quoted context omitted.

An aside to the aside: I did too, until I exported my Goodreads ratings and uploaded the CSV. Then it's pretty great.

You can usually do with less than the full history. "Here are five books where I liked the tone/setting/worldbuilding/topic, gimme more" has proven pretty successful. With gradual refinement - "I like #1 and #4, but I wonder if something like that exists with a 40s scifi tone. Gimme your top 10" It's... mostly worked out so far. (It also turns out that some topics, I seem to have thoroughly explored. Taking recommend…

Huh, I’ve struggled with your suggested strategy. Maybe it’s a skill issue :)

Re: ChatGPT Atlas

#483

Post by serbuvlad »

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”.

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

Re: ChatGPT Atlas

#484

Post by supportengineer »

bobviolier wrote: post #439
baal80spam wrote: post #355

Earlier quoted context omitted.

Ah, makes sense why I need to use an extension for that: > To use this feature, you must be located in the US

I just don't get this. Google has SO MANY THINGS that are US only. While most other companies release things to everyone (like OpenAI). How does Google expect to compete with OpenAI globally if they keep limitting the rest of the world?

Maybe those features are illegal in every other country.

Re: ChatGPT Atlas

#485

Post by patapong »

elric wrote: post #350
granzymes wrote: post #279

Earlier quoted context omitted.

Being able to search browser history with natural language is the feature I am most excited for. I can't count the number of times I've spent >10 minutes looking for a link from 5 months ago that I can describe the content of but can't remember the title.

Are we talking searching the URLs and titles? Or the full body of the page? The latter would require tracking a fuckton of data, including a whole lot of potentially sensitive data.

Opera had the latter before switching to Chromium... I miss it.

Re: ChatGPT Atlas

#486

Post by teunlao »

Chromium fork with AI sidebar. Revolutionary? No. The limits-for-default-browser bait though - that's actual strategy. Will people stay after seven days? My guess most won't.

Re: ChatGPT Atlas

#488

Post by gnarlouse »

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 linear conversational format, and it just isn't functional.

Blows my mind that with all the great big AI minds at OpenAI they still can't do basic functionality.

-- edit --

Like seriously, for some of us old heads, imagine having this in undergrad: a professor in your pocket that can handle your arbitrarily stupid recitation questions, one on one, with infinite patience. I think I could have aced electrodynamics and Calc III instead of just pulling Bs.

Re: ChatGPT Atlas

#489

Post by nsonha »

bilsbie wrote: post #286

Super dumb question but why was this so hard for someone to build. I’ve been wanting to simply ask AI about whatever is currently on my screen for years. I don’t get why we can’t easily have this.

We have this though, as a (controversial) built-in Windows's feature called "Recall". We have many apps like that (vercept.com) and MCP servers that do that. It's just, besides privacy concerns, it doesn't works well yet for agentic usecases.

Re: ChatGPT Atlas

#490

Post by rlander »

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…

Maybe you haven’t seen this yet, but there is a (recent) option to fork a conversation when you click on the thee dots of a reply.
Post reply on HN