Live data from Hacker News

AI tools I wish existed

sharif.io

81–90 of 112 posts

Re: AI tools I wish existed

#81
>A calorie tracking app that’s a chat app grounded by nutrition databases. Just minimize the cognitive effort it takes me to log a meal.

My brother in christ, how much cognitive effort does it take to log a meal??

Re: AI tools I wish existed

#82
Many of these ideas depend on knowing the user’s preferences, patterns, communications, events and health. This is where the opportunity lies for Apple - the phone and watch know so much about you, that Apple could focus on smartly assembling the context for various LLM interactions, in a privacy-preserving way.

Re: AI tools I wish existed

#83
post #62

Earlier quoted context omitted.

They do work, extremely well, not for us though!

Do you not think that’s what the post meant? That it could work for us rather than them?

They probably won’t though. The commercial LLMs will be tuned to work for them as well soon. And your local LLM won’t be allowed to scrape the internet since it’s all locked down now.

Re: AI tools I wish existed

#84
post #13

Not just for this article, but from most ideas/articles around LLMs, I feel like they aren't "thinking with portals" enough. We have "portal gun" tech (or at least, that's what's being marketed), and we're using it as better doors.

I agree with this. But do you have any resources on "thinking with portals"? It's easier said than done.

Sadly, I don't. If I did I'd be busy building it rather than judging others on HN.

But it's a bit telling that OpenAI themselves can only come up with a better ~door~ ads.

Re: AI tools I wish existed

#86
A few of them imply a vision model which can control your keyboard and mouse. Offline-only of course.

It could help with most tech support questions.

We could select text and ask to fact check or explain to layperson or search more.

It could get around cookie banners and dark patterns.

It could do my time tracking and tell me to get off HN and optimize Pomodoro-style breaks.

It could write scripts after watching me switch between multiple pages of AWS services.

Re: AI tools I wish existed

#87
post #78

On the topic of "24. A Sony Walkman-style device that you can give to children so they can ask questions to an LLM...", I would strongly caution against this: - short of AGI, what a child will hear are explanations given with authority, which would probably be correct a very high percentage of the time (maybe even close to or above 99%), BUT the few incorrect answers and subtles misconceptions finding their way in th…

Just two days ago, I asked ChatGPT to provide an explanation of the place-value system that my six-year-old could understand. The only problem was that it mixed up digit value and place value, which caused it to become confused. I spotted the mistake, and ChatGPT apologised, as it usually does. But if my six-year-old had asked it first, she wouldn't have noticed.

I'm not sure how much misinformation my child would learn as truth from this device.

Re: AI tools I wish existed

#89
post #15

There's some sort of fundamental category mistake going on with thinking like this. Most of the items in this list fall prey to it, but it is maybe best exemplified by this one: > A writing app that lets you “request a critique” from a bunch of famous writers. What would Hemingway say about this blog post? What did he find confusing? What did he like? Any app that ever claimed to tell you what "Hemingway would say ab…

> So in effect it becomes an exercise of "can you fool the human into thinking this is a plausible thing Hemingway would've said". That's useful in itself, though. Assume the human knows they're "being fooled", we call this make-believe, or suspending disbelief. It's a tool we use each time we act something out, pretend to be someone else, try to put ourselves in their position; we do that when we try to learn from r…

Very interesting rebuttal. I must say I was almost as convinced by the original post! This just made me think: if we can’t agree even on relatively simple topics like this, what hope is there that we will ever agree on most important issues. Disagreement should be an expected constant in all aspects of life, not an undesirable outcome. Even with disagreement, I believe it’s possible to find common ground and do what needs to be done (now I am really far into my tangential point!)
Post reply on HN