Hacker News Reader

Comment by hvs | Hacker News Reader

It has helped me learn things more interactively because I can ask questions and get answers without having to read 10 blog posts or a book before understanding things. For my personality, it would be hard to recreate without having a living mentor available 24/7 that had knowledge of everything I wanted to ask of it.

Does it get things wrong? Sure. But generally the subtle ways it might get stuff wrong would be the way I would subtly misunderstand things while learning. So, it's definitely not perfect, but "not letting perfect be the enemy of good" and all that.

View on HN

You must have missed the article posted this morning where ChatGPT complexity invented a sexual allegation against a law professor including citing a fictional news article that never existed. I wouldn’t call that a subtle misunderstanding.

I'm not asking for lists of sexual allegations, I'm asking about technical concepts. Very different.

So it's the Weekly World News... And yea, we've had rags before AI was made too.

Yes, chatGPT hallucinates facts and is not great at causal inference chains. The interactivity is the real boon as what I can do is query the chat bot, and then explore the results either with traditional research or with more queries and exploration. It's a really fun and productive way to learn.

It's shocking to me how many people are treating chatGPT as a reliable source given how much we know it hallucinates.

Because very few people ever stop and take account of how monstrously unreliable people are.

At the same time I can ask GPT to write a script, reflect on its output, and it takes about 95% of the work I need to do out of script writing.

But... How much does it hallucinate? Are there safer areas or ways of asking questions, than others? Genuine question. I found that when I ask simple factual questions in a... "non pushy non presumptive" manner, it gives accurate basic answers in areas I'm familiar with. I ask it simple things about basic French or basic Python or basic music theory and so far it's been... brilliant!

I found most examples of hallucination on the web to be pushy or presumptive or edgy I. E. "tell me the ways in which vaccines cause male pattern baldness" and then manipulate prompts.

So I assume there are areas and approaches that are safer and more useful, and areas and approaches that are riskier?

It's shocking to me how many people are treating Google Search as a reliable source given how much we know it silos people into extremist sites, and has been extensively gamed by SEO professionals.

Reply on news.ycombinator.com