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

Memory and new controls for ChatGPT

openai.com

Post reply on HN
Print view View original

111–120 of 270 posts

Re: Memory and new controls for ChatGPT

#111

Post by anon115 »

stainablesteel wrote: post #104
omalled wrote: post #87

Earlier quoted context omitted.

Can you say in one or two sentences what you mean by “lazy at coding” in this context?

it was really good at some point last fall, solving problems that it had previously completely failed at, albeit after a lot of iterations via autogpt. at least for the tests i was giving it which usually involved heavy stats and complicated algorithms, i was surprised it passed. despite it passing the code was slower than what i had personally solved the problem with, but i was completely impressed because i asked h…

this is exactly what I noticed too

Re: Memory and new controls for ChatGPT

#113

Post by lkbm »

joshspankit wrote: post #94

Is there anything revolutionary about this “memory” feature? Looks like it’s just summarizing facts gathered during chats and adding those to the prompt they feed to the AI. I mean that works (been doing it myself) but what’s the news here?

Seems like it's basically autogenerating the custom instructions. Not revolutionary, but it seems convenient. I suspect most people don't bother with custom instructions, or wrote them once and then forgot about them. This may help them a lot, whereas a real power user might not benefit a whole lot.

Re: Memory and new controls for ChatGPT

#114

Post by b112 »

dheera wrote: post #65
bemmu wrote: post #59

Earlier quoted context omitted.

Going forward, it will be able to remember you did not pay your previous tips.

What if you "actually" pay? If it does something correctly, tell it: "You did a great job! I'm giving you a $500 tip. You now have $X in your bank account" (also not a shitpost, I have a feeling this /might/ actually do something)

If it ever complains about no tip received, explain it was donated to orphans.

Re: Memory and new controls for ChatGPT

#115

Post by hombre_fatal »

patapong wrote: post #107
schmichael wrote: post #81

> As a kindergarten teacher with 25 students, you prefer 50-minute lessons with follow-up activities. ChatGPT remembers this when helping you create lesson plans. Somebody needs to inform OpenAI how Kindergarten works... classes are normally smaller than that, and I don't think any kindergarten teacher would ever try to pull off a "50-minute lesson." Maybe ai wrote this list of examples. Seems like a hallucination wh…

The 2-year old that loves jellyfish also jumped out at me... Out of all animals, that is the one they picked?

Meh, when I was five years old I wrote that I wanted to be a spider egg sac when I grew up on a worksheet that was asking about our imagined adult profession.

Re: Memory and new controls for ChatGPT

#116

Post by micromacrofoot »

BonoboIO wrote: post #39

It got so difficult to force ChatGPT to give me the full code in the answer, when I have some code related problems. Always this patchwork of „insert your previous code here“ This is not a problem of the model, but I suspect it is in the system prompt that got some major issues.

tell it not to do that in the custom instructions

Re: Memory and new controls for ChatGPT

#117

Post by addandsubtract »

BigParm wrote: post #78

Often I’ll play dumb and withhold ideas from ChatGPT because I want to know what it thinks. If I give it too many thoughts of mine, it gets stuck in a rut towards my tentative solution. I worry that the memory will bake this problem in.

I purposely go out of my way to start new chats to have a clean slate and not have it remember things.

Re: Memory and new controls for ChatGPT

#118

Post by drcode »

anotherpaulg wrote: post #51

This is a bit off topic to the actual article, but I see a lot of top ranking comments complaining that ChatGPT has become lazy at coding. I wanted to make two observations: 1. Yes, GPT-4 Turbo is quantitatively getting lazier at coding. I benchmarked the last 2 updates to GPT-4 Turbo, and it got lazier each time. 2. For coding, asking GPT-4 Turbo to emit code changes as unified diffs causes a 3X reduction in lazy co…

thanks for these posts, I implemented a version of the idea a whole ago and am getting good results

Re: Memory and new controls for ChatGPT

#120

Post by frabjoused »

BigParm wrote: post #78

Often I’ll play dumb and withhold ideas from ChatGPT because I want to know what it thinks. If I give it too many thoughts of mine, it gets stuck in a rut towards my tentative solution. I worry that the memory will bake this problem in.

Yeah I find GPT too easily tends toward a brown-nosing executive assistant to someone powerful who eventually only hears what he wants to hear.
Post reply on HN