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

131–140 of 270 posts

Re: Memory and new controls for ChatGPT

#131

Post by joshspankit »

nafizh wrote: post #86
OJFord wrote: post #62

Earlier quoted context omitted.

I haven't really tried to use it for coding, other than once (recently, so not before some decline) indirectly, which I was pretty impressed with: I asked about analyst expectations for the Bank of England base rate, then asked it to compare a fixed mortgage with a 'tracker' (base rate + x; always x points over the base rate). It spat out the repayment figures and totals over the two years, with a bit of waffle, and…

To be honest, when I say it has significantly worsened, I am comparing to the time when GPT-4 just came out. It really felt like we were on the verge of 'AGI'. In 3 hours, I coded up a complex piece of web app with chatgpt which completely remembered what we have been doing the whole time. So, it's sad that they have decided against the public having access to such strong models (and I do think it's intentional, not…

Have you tried feeding the exact same prompt in to the API or the playground?

Re: Memory and new controls for ChatGPT

#132

Post by Judgmentality »

cooper_ganglia wrote: post #110
dheera wrote: post #65

Earlier quoted context omitted.

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)

Gaslighting ChatGPT into believing false memories about itself that I’ve implanted into its psyche is going to be fun.

I guess ChatGPT was the precursor to Bladerunner all along.

Re: Memory and new controls for ChatGPT

#133

Post by mistermann »

asaddhamani wrote: post #95
Me1000 wrote: post #89

Earlier quoted context omitted.

It has a tendency to do: "// ... the rest of your code goes here" in it's responses, rather than writing it all out.

It's incredibly lazy. I've tried to coax it into returning the full code and it will claim to follow the instructions while regurgitating the same output you complained about. GPT-4 was great, GPT-4 Turbo first version was pretty terrible bordering on unusable, then they came out with the Turbo second version, which almost feels worse to me, though I haven't compared, but if someone comes claiming they fixed an issue…

I have a feeling full powered LLM's are reserved for the more equal animals.

I hope some people remember and document details of this era, future generations may be so impressed with future reality that they may not even think to question it's fidelity, if that concept even exists in the future.

Re: Memory and new controls for ChatGPT

#134

Post by comboy »

bluish29 wrote: post #28

It is already ignoring your prompt and custom instructions. For example, If I explicity ask it to provide a code instead of an overview it will respond by apologizing and then provide the same overview answer with minimal if no code. Will memory provide a solution to that or will be a different thing to ignore?

It used to respect custom instructions soon after GPT4 came out. I have instruction that it should always include [reasoning] part which is meant not to be read by the user. It improved quality of the output and gave some additional interesting information. It never does it know even though I never changed my custom instructions. It even faded away slowly along the updates.

In general I would be much more happy user if it haven't been working so well at one point before they heavily nerfed it. It used to be possible ta have a meaningful conversation on some topic. Now it's just super eloquent GPT2.

Re: Memory and new controls for ChatGPT

#135

Post by jerpint »

addandsubtract wrote: post #117
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.

Agreed, I do this all the time especially when the model hits a dead end

Re: Memory and new controls for ChatGPT

#136

Post by anotherpaulg »

minimaxir wrote: post #45
bluish29 wrote: post #28

It is already ignoring your prompt and custom instructions. For example, If I explicity ask it to provide a code instead of an overview it will respond by apologizing and then provide the same overview answer with minimal if no code. Will memory provide a solution to that or will be a different thing to ignore?

Did you try promising it a $500 tip for behaving correctly? (not a shitpost: I'm working on a more academic analysis of this phenomenon)

I actually benchmarked this somewhat rigorously. These sort of emotional appeals actually seem to harm coding performance.

https://aider.chat/docs/unified-diffs.html

Re: Memory and new controls for ChatGPT

#137

Post by akdor1154 »

mistermann wrote: post #133
asaddhamani wrote: post #95

Earlier quoted context omitted.

It's incredibly lazy. I've tried to coax it into returning the full code and it will claim to follow the instructions while regurgitating the same output you complained about. GPT-4 was great, GPT-4 Turbo first version was pretty terrible bordering on unusable, then they came out with the Turbo second version, which almost feels worse to me, though I haven't compared, but if someone comes claiming they fixed an issue…

I have a feeling full powered LLM's are reserved for the more equal animals. I hope some people remember and document details of this era, future generations may be so impressed with future reality that they may not even think to question it's fidelity, if that concept even exists in the future.

> I hope some people remember and document details of this era, future generations may be so impressed with future reality that they may not even think to question it's fidelity, if that concept even exists in the future.

The former sounds like a great training set to enable the latter. :(

Re: Memory and new controls for ChatGPT

#138

Post by joshuacc »

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…

> classes are normally smaller than that

This varies a lot by location. In my area, that's a normal classroom size. My sister is a kindergarten teacher with 27 students.

Re: Memory and new controls for ChatGPT

#139

Post by bbor »

Me1000 wrote: post #89
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 has a tendency to do: "// ... the rest of your code goes here" in it's responses, rather than writing it all out.

It’s so interesting to see this discussion. I think this is a matter of “more experienced coders like and expect and reward that kind of output, while less experienced ones want very explicit responses”. So there’s this huge LLM Laziness epidemic that half the users cant even see

Re: Memory and new controls for ChatGPT

#140

Post by bbor »

mistermann wrote: post #133
asaddhamani wrote: post #95

Earlier quoted context omitted.

It's incredibly lazy. I've tried to coax it into returning the full code and it will claim to follow the instructions while regurgitating the same output you complained about. GPT-4 was great, GPT-4 Turbo first version was pretty terrible bordering on unusable, then they came out with the Turbo second version, which almost feels worse to me, though I haven't compared, but if someone comes claiming they fixed an issue…

I have a feeling full powered LLM's are reserved for the more equal animals. I hope some people remember and document details of this era, future generations may be so impressed with future reality that they may not even think to question it's fidelity, if that concept even exists in the future.

…could you clarify? Is this about “LLMs can be biased, thus making fake news a bigger problem”?
Post reply on HN