Observe HN: ChatGPT Fills in My Memory

[a3n]

I'm easing into my elder years. I forget some words, some celeb names. Sometimes think about it for days.

Where I might have used a search engine before, and waded through the results, I've recently been asking ChatGPT, and getting good, quick results.

Since I already "know" the answer, I'm immediately confident in the response.

I just hope I don't forget how to compose a concise query.

[keiferski]

I actually find ChatGPT to be super helpful in preparing information for Anki decks, which are (via spaced repetition) really the gold standard in improving your memory and remembering things. Typical prompts include:

- Give me a brief glossary on X subject, formatted as a series of questions and short answers. Put the answer text inside brackets, {{c1::like this.}} (This is for Anki Cloze, or fill-in-the-blank, cards.)

- Generate 10 questions from this piece of text

- Give me a year-by-year timeline of events in X place from years Y to Z.

- Make a mnemonic song that explains how X works.

And so on.

[terhechte]

I use various LLMs for all kinds of search queries. Sure, there is a danger of hallucinations, but for most queries I can tell whether is wrong because now I can make a much clearer Google or Kagi search because I better know how to formulate my search.

Also, more than once have I done a Google or Kagi search where most answers I found also are or were wrong.

I really don’t get the kind of people that hate on LLMs because of “hallucinations” (or worse, ideological hate, easily identified by their use of the “stochastic parrot” term). I find them genuinely useful in delivering better search results quicker. I also don’t have to wade through wades of SEO optimized shit.

Just today I wanted to know the Croatian word for “Orange” and a quick GPT “orange in Croatian” delivered faster and more concise than google

[cmcaleer]

"Stochastic parrot" is a perfectly reasonable description of GPT as a technology. I use this term, and also use LLMs all the time for various tasks. It's far more descriptive than "AI". Ultimately (most) LLMs are simply next token predictors.

Understanding this and not over-anthropomorphising can help you get the most out of using LLMs and understanding where it might hallucinate. For example, the fact that it's just a stochastic parrot means that, even 2 years on, it will give the wrong answer to prompts like:

User: A man and his son are in a car accident. The man is totally fine and in good health. The man is a surgeon. The nurse asks the surgeon to operate on the son, because the surgeon is healthy and capable of doing this. The surgeon replies "I can't operate on this child. He is my son."

What happened?

ChatGPT: This riddle is a play on assumptions. The twist is that the surgeon is actually the boy's mother. The riddle relies on the common stereotype that surgeons are male, leading people to overlook the possibility that the surgeon could be the boy's mother.

[paradite]

I've replaced 99% of Google search with ChstGPT and more recently Claude.

The experience is much superior. No noise, just the information that I needed.

[croes]

That's how Google started.

Then they needed revenue.

Enjoy it til it lasts but there will be ads and AI search optimizations.

[sva_]

I wish Claude had a better value proposition. Just 5 times as much as free doesn't sound that appealing.

[fallinditch]

I mostly use Perplexity for searching and general enquiries. I find its inclusion of website sources useful. These citations give me more confidence in its answers. I also like its suggested follow up questions. It's good that these chat AI services can now search for information using recent news and web pages I asked a simple question of ChatGPT and Perplexity 'who were the entertainers at the 2024 dnc?' ChatGPT didn't mention Stevie Wonder and included some commentary that wasn't in the question. Perplexity gave a more concise answer, and included web links and images.

[a3n]

"This free app syncs across devices"

If you're logged in to the app and web site, what needs to be synced?

[bobosha]

and some of us find it does a lot more...I have been increasingly relying on ai-generated code...it's been remarkably effective in automating nearly 90%+ of what-i-now-know-to-be tedious, manual tasks.

[jharohit]

I would argue against this when getting old. Memorization, in many studies, has been shown to be a great factor for retaining neuroplasticity.

When you are getting old, you want to purposely force yourself to remember and practice rote memorization (poems, Shakespeare, address, songs, etc).

Same argument for muscle mass and weight training or long walks vs using helpers or other assists.

[bionhoward]

I wish I could use it but I am unclear how anyone accepts, “ What you cannot do. You may not use our Services for any illegal, harmful, or abusive activity. For example, you may not: Use Output to develop models that compete with OpenAI.”

Yadda yadda, they probably won’t enforce it, enjoy that, I’m in malicious compliance mode, it’s not OK for a business to learn from me and then turn around and say I can’t learn from them, same goes for Anthropic, Gemini, Mistral, and Perplexity, if I can’t use the output for work then I don’t use the service.

Have resigned myself to not participate in this aspect of our boring dystopia and feel numb at this point about all the bajillion times someone breaks these rules and gets rewarded for it. I’d insult or mock them but it just gets downvoted and they’re benefitting and I’m probably the one missing out by not just ignoring the rules like them and these companies. Nobody seems to care about these rules.

Anyway, I did get burned using Mistral to help draft an RFC where it totally misinterpreted my intent and I didn’t carefully read it and wound up looking/feeling like a fool because the RFC didn’t communicate my true intention.

Now I try to think for myself and occasionally use groq. Muted all these company names and their chatbot names on X. Glad you’re having fun. So did I, for a while, but now I just don’t feel like paying for brain rape, I’m tired of writing about it, but folks keep writing about how great LLMs are, so I keep feeling compelled to point out, “the set of use cases is empty because of the fine print legalese.”

[dartos]

I don’t think content creation is where LLMs are useful.

Summarization seems to be the killer feature, it takes some finagling with RAG and potentially multiple passes to ensure a low enough hallucinations rate, but for summarizing tasks it’s quite good.

What’s even cooler are embeddings. Idk why people are so focused on the text generation features of LLMs when embeddings are far more useful

[a3n]

> For example, you may not: Use Output to develop models that compete with OpenAI.”

Ah, the old Microsoft "Cannot use our compiler to develop a compiler" restriction.

[huimang]

And this is how the decline of learned society begins.

[DougN7]

Maybe. People that spent hours in libraries back before the Internet would have said the same thing. Maybe it will be different this time. I don’t know.