Ask HN: What are some actual use cases of AI Agents right now? • Hacker News Board

Re: Ask HN: What are some actual use cases of AI Agents right now?

#151

Post by ltengelis » Fri, Feb 16, 2024, 3:47 PM UTC

qeternity wrote: post #61

skywhopper wrote: post #45

Earlier quoted context omitted.

You use them successfully because your human mind can filter out the junk. It would only take one inaccurate API call that charges your credit card $10k or sells your car for 10 cents to cause a lot of damage to your life.

Which is why even with classical software, most of us don't have APIs where that's all it takes.

Frankly I think you've said it all here - a properly designed API + a well designed LLM interface on top of that enables non-technical people to do things they otherwise couldn't.

Re: Ask HN: What are some actual use cases of AI Agents right now?

#152

Post by jazzyjackson » Sat, Feb 17, 2024, 11:22 AM UTC

vintermann wrote: post #120

chenxi9649 wrote: post #43

Earlier quoted context omitted.

Yea that's a good point. Now I am curious, what are some tasks that can accept a model that is at 80% as good as a human, but is 100x cheaper?(or, 100x faster?)

Well, an old one is OCR, especially handwritten OCR. I'm doing genealogy. There is SO MUCH old handwritten material that is never transcribed, and which requires special expertise to read (old and exotic handwriting styles) and interpret (place names, writing conventions, abbreviations). It doesn't have to be perfect. It's not as if the actual data in there is perfect. It just has to be in a form where I can search i…

bruh what are the retirees supposed to do once you've automated their hobby

Re: Ask HN: What are some actual use cases of AI Agents right now?

#153

Post by bitnasty » Sat, Feb 17, 2024, 12:30 PM UTC

renonce wrote: post #149

PheonixPharts wrote: post #37

> I'd love to know what are some of the hidden challenges to making a useful product with agents? One thing that is still confusing to me, is that we've been building products with machine learning pretty heavily for a decade now and somehow abandoned all that we have learned about the process now that we're building "AI". The biggest thing any ML practitioner realizes when they step out of a research setting is that…

The last widely used AI tool was facial recognition, a technology widely used in fields such as company clock-ins, access control, surveillance, and more, and it is so trusted that facial recognition is often the sole method for clocking in. These facial recognition systems can maintain an extremely high accuracy rate for every entry and exit of thousands of people in a database every day. Now when will LLMs achieve…

They have… they write language and they are good at it. The problem is language is not reality, proper language does not mean truth or fact. The models predict what is most likely to come next, not what is most likely to reflect reality.

Re: Ask HN: What are some actual use cases of AI Agents right now?

#154

Post by nomel » Mon, Feb 19, 2024, 11:00 PM UTC

bitnasty wrote: post #153

renonce wrote: post #149

Earlier quoted context omitted.

The last widely used AI tool was facial recognition, a technology widely used in fields such as company clock-ins, access control, surveillance, and more, and it is so trusted that facial recognition is often the sole method for clocking in. These facial recognition systems can maintain an extremely high accuracy rate for every entry and exit of thousands of people in a database every day. Now when will LLMs achieve…

They have… they write language and they are good at it. The problem is language is not reality, proper language does not mean truth or fact. The models predict what is most likely to come next, not what is most likely to reflect reality.

> what is most likely to come next

> not what is most likely to reflect reality.

Shouldn't there be a strong statistical correlation between the two? And, isn't that, fundamentally, more about intent of the training? If I train a model to predict what comes next in reality, it's through next word prediction, but it is predicting what reflects reality the best.