←back to thread

ChatGPT Atlas

(chatgpt.com)
763 points easton | 10 comments | 21 Oct 25 17:18 UTC | HN request time: 0.005s | source | bottom
Show context
ZeljkoS ◴[21 Oct 25 18:02 UTC] No.45659245[source]▶
Here are the highlights from the .DMG installer screens (https://imgur.com/a/Tu4TlNu):

1. Turn on browser memories Allow ChatGPT to remember useful details as you browse to give smarter responses and proactive suggestions. You're in control - memories stay private.

2. Ask ChatGPT - on any website Open the ChatGPT sidebar on any website to summarize, explain, or handle tasks - right next to what you're browsing.

3. Make your cursor a collaborator ChatGPT can help you draft emails, write reviews, or fill out forms. Highlight text inside a form field or doc and click the ChatGPT logo to get started.

4. Set as default browser BOOST CHATGPT LIMITS Unlock 7 days of extended limits on messaging, file uploads, data analysis, and image generation on ChatGPT Atlas.

5. You're all set — welcome to Atlas! Have fun exploring the web with ChatGPT by your side, all while staying in control of your data and privacy. (This screen also displays shareable PNG badge with days since you registered for ChatGPT and Atlas).

My guess is that many ChatGPT Free users will make it their default browser just because of (4) — to extend their limits. Creative :)

replies(9): >>45659596 #>>45659838 #>>45659864 #>>45659877 #>>45660265 #>>45662102 #>>45662218 #>>45663663 #>>45663733 #
ghostpepper ◴[21 Oct 25 21:43 UTC] No.45662102[source]▶
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.

replies(10): >>45662292 #>>45662400 #>>45662568 #>>45662756 #>>45663817 #>>45664726 #>>45665826 #>>45665934 #>>45666808 #>>45668406 #
sheepscreek ◴[21 Oct 25 22:53 UTC] No.45662756[source]▶
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”.
replies(4): >>45663063 #>>45663318 #>>45663629 #>>45663911 #
1. nostromo ◴[22 Oct 25 01:23 UTC] No.45663911[source]▶
I have the same issue.

I often get annoyed with ChatGPT yammering on and on, so I repeatedly told it to cut to the chase and speak more succinctly.

Now it just says "I'll get right to the point..." and then still yammers on and on unabated.

replies(4): >>45664291 #>>45664468 #>>45666302 #>>45666414 #
2. a2dam ◴[22 Oct 25 02:31 UTC] No.45664291[source]▶
This happened to me too. I eliminated it in text responses, but eventually figured out that there's a system prompt in voice mode that says to do this (more or less) regardless of any instructions you give to the contrary. Attempting to override it will just make it increasingly awkward and obvious.
replies(1): >>45667971 #
3. prawn ◴[22 Oct 25 02:59 UTC] No.45664468[source]▶
I add "Terse, no commentary" to a request, which it will obey, but then immediately return to yammering in a follow-up message. However, this is in Incognito; maybe there's a setting when logged in.
replies(2): >>45665237 #>>45666948 #
4. distances ◴[22 Oct 25 05:37 UTC] No.45665237[source]▶
You can add a custom instruction in settings. That works pretty well, applies to all chats. Memory feature I of course disabled as soon as it was released so I don't know which takes precedence.
5. fakwandi_priv ◴[22 Oct 25 08:33 UTC] No.45666302[source]▶
Might not be the best fix but other than disabling memory I changed the setting ‘ChatGPT personality’ to ‘Robot’ and I’ve always had straight to the point answers (so far).
replies(1): >>45668071 #
6. muddi900 ◴[22 Oct 25 08:52 UTC] No.45666414[source]▶
LLMs are like children; telling them to not do something puts the idea in their 'head'.

Instead, telling them to do the opposite works. "Brevity is appreaciated", or "Preserve Tokens and be concise."

replies(1): >>45667872 #
7. phatfish ◴[22 Oct 25 10:07 UTC] No.45666948[source]▶
With GPT5 there is a persona (I think, I forget what the call it) setting, I chose "Robot" and that shut it up pretty well.
8. portaouflop ◴[22 Oct 25 12:13 UTC] No.45667872[source]▶
It’s called the waluigi problem and is also part of the reason why you can never fully “censor” an LLM; there is always some jailbreak possible
9. transcriptase ◴[22 Oct 25 12:24 UTC] No.45667971[source]▶
I went from using voice mode near-exclusively for brainstorming and planning out projects to giving up on voice altogether because of this very thing.
10. OneOffAsk ◴[22 Oct 25 12:32 UTC] No.45668071[source]▶
Yeah, ChatGPT is a tool not a therapist with robot mode on and all memory options disabled. It’s awesome.