Hacker News Reader

Comment by louiereederson | Hacker News Reader

Late last year I tried asking ChatGPT to summarize a collection of 10 researchers' views/findings on a topic and provide representative quotes. It initially looked plausible but when I checked the links, the quotes were from clearly AI generated summaries of actual interviews. The paraphrasing was also plausible but subtly and profoundly incorrect.

I haven't tested this again on the latest models though, so not sure if there's been an improvement.

View on HN

That's more or less how it works. To actually have the system carry out your intention it would have to use significant hardware resources (and even then who knows if it would actually work). Alternatively you would need to break up the work into chunks that the hardware allocated to you by the system would not be overwhelmed.

A lot of people don't realize this because the work that they are having the AI do does not need to be either true or false. It just has to output media that seems like it fits. The system probably took many shortcuts to keep the resource use low while outputting something plausible but false.

And frankly this is sort of fine as long as you know what it's doing and what the limitations are. Hypothetically if you broke up the task into multiple steps that the system can actually ingest properly it might reduce the time that the task took overall, maybe even significantly, but not down to one prompt.

Claude has a research mode. I tried using it multiple times in the domains that I know quite well. Basically, used it with the hopes to save me time by aggregating the information I needed. I used it multiple times with different approaches and it never did anything useful. Full of factually incorrect and outdated information. I know that I could never hope to even slightly trust it for anything I don't have knowledge in.

ChatGPT is horrible overall, for sure, but how exactly did you ask it to summarize, and what model was it exactly?

(I'm not saying "you're holding it wrong", I'm asking "how were you holding it"?

Did you tell it to pull in the sources, did it do so automatically, or were you working from just the base weights? )

Reply on news.ycombinator.com