News for hackers. Stuff that matters.
Re:ChatGPT Atlas by sheepscreek on Tuesday October 21, 2025 @06:53PM (#45662756)
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”.
Re:ChatGPT Atlas by NikolaNovak on Tuesday October 21, 2025 @07:58PM (#45663318)
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 by sheepscreek on Wednesday October 22, 2025 @12:44AM (#45664962)
It was something I instructed it once and forgot about. When I checked in the settings under “memories” I finally discovered the culprit and removed it.

I’m not sure about voice chat, though - it’s equally frustrating for me. Often, it’s excessively verbose, repeating my question with unnecessary commentary that doesn’t contribute to the answer. I haven’t tried the personality tweaks they recently introduced in the settings - I wonder if those also affect voice chat, because that could be a potential solution.

Re:ChatGPT Atlas by serbuvlad on Tuesday October 21, 2025 @07:25PM (#45663063)
ChatGPT gets about 2-3x as smart the second you turn off memories.
Re:ChatGPT Atlas by mtillman on Tuesday October 21, 2025 @07:52PM (#45663277)
That’s funny. Your phrasing reminds me of a Zappa line “dumb all over and a little ugly on the side”.
Re:ChatGPT Atlas by visarga on Tuesday October 21, 2025 @08:38PM (#45663629)
I hate that. ChatGPT makes itself sound smarter through compression and insider phrasing, and the output is harder to read without adding real clarity. That's why I can't use o3 or GPT-5. The performance layer gets in the way of the actual content, and it's not worth parsing through. I'm mostly avoiding it now.
Re:ChatGPT Atlas by nostromo on Tuesday October 21, 2025 @09:23PM (#45663911)
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.

Re:ChatGPT Atlas by prawn on Tuesday October 21, 2025 @10:59PM (#45664468)
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.
Re:ChatGPT Atlas by distances on Wednesday October 22, 2025 @01:37AM (#45665237)
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.
Re:ChatGPT Atlas by phatfish on Wednesday October 22, 2025 @06:07AM (#45666948)
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.
Re:ChatGPT Atlas by jgruber on Friday October 24, 2025 @11:36PM (#45701190)
Same. The GPT5 “Robot” persona does what no custom “be terse”, “no fluff”, etc. custom prompt ever could. It actually makes ChatGPT terse and to-the-point and eliminates (or at least greatly reduces) fluff. I love it.
Re:ChatGPT Atlas by a2dam on Tuesday October 21, 2025 @10:31PM (#45664291)
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.
Re:ChatGPT Atlas by transcriptase on Wednesday October 22, 2025 @08:24AM (#45667971)
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.
Re:ChatGPT Atlas by fakwandi_priv on Wednesday October 22, 2025 @04:33AM (#45666302)
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).
Re:ChatGPT Atlas by OneOffAsk on Wednesday October 22, 2025 @08:32AM (#45668071)
Yeah, ChatGPT is a tool not a therapist with robot mode on and all memory options disabled. It’s awesome.
Re:ChatGPT Atlas by muddi900 on Wednesday October 22, 2025 @04:52AM (#45666414)
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."

Re:ChatGPT Atlas by portaouflop on Wednesday October 22, 2025 @08:13AM (#45667872)
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