Hacker News Reader

Comment by itchyjunk | Hacker News Reader

For a subset of topics, "AI" is already what I prefer to interact with over humans. At times, it's nicer to start with "AI" and kind of ground my messy thoughts before interacting with people and that works better than directly starting with a person.

I'm also starting to come across people who say "You should ask these types of questions to AI first" answer. But this is no different than people who preached "lmfgt" kind of religiously. Even when I prefer to start with humans, some humans prompt me to start by prompting AI.

View on HN

I see the same.

I'm waiting on LLMs to get good enough that I can use them to help me learn foreign languages - e.g. talk to me about the news in language X. This way I can learn a language in an interesting and interactive way without burdening some poor human with my mistakes. I would build this myself but others will probably beat me too it.

I sometimes prompt the LLM to talk to me as a <language> instructor - to suggest a topic, ask a question, read my response, correct my grammar, and suggest alternate vocabulary where appropriate. This works quite well. Similar to your comment, I am often hesitant to butcher a language in front of a real person :-).

The problem is, AI doesn't let you, or encourage you to create your own style. Word choices, structure, flow, argument building and discourse style is very fixed and "average", since it's a machine favors what it ingests most.

I use Grammarly for grammar and punctuation, and disable all style recommendations. If I let it loose on my piece of text, it converts it to a slop. Same bland, overly optimistic toned text generator output.

So, that machine has no brain, use your own first.

I contribute to a language-learning forum as a native English speaker, and we constantly get questions from people who are doing exactly what you're doing. The AI does not understand the language, and it will tell you blatantly incorrect information. Especially with less-common constructs, you'll just get very bad advice.

The first step to really learn a language is to be confident and forgive yourself for any mistakes (you’re starting late anyway , and juggling other things).

These days, I do my best to learn and reflect. But any mistakes is just a reminder for more learning (and practice).

> forgive yourself for any mistakes (you’re starting late anyway)

Do you think babies don't make mistakes?

They do, but they also don’t care. Adults tend to do care about that.

So what's the idea behind "you're starting late"?

LLMs are already good enough to tell you the news in language X and listen to your broken attempts at asking questions back. Or what's missing?

They do seem close to being able to, I'm mostly waiting on someone to provide it as a service - I don't have time for side projects ATM.

It's not a project. Just open Claude or ChatGPT and tell it what you want to do. You could copy/paste your comment above. If you want to get slightly more fancy, use Google's AIStudio with a simple system prompt.

I would like to do it semi-passively through talking while I’m doing other things like going for a walk, doing chores etc. I don’t have the time at the moment to sit down and focus on this.

Reply on news.ycombinator.com