Live data from Hacker News

Three kinds of AI products work

seangoedecke.com

31–40 of 130 posts

Re: Three kinds of AI products work

#31
post #8

So the only AI products that work is a chat bot you can talk to, or a chat bot that can perform tasks for you. Next thing you'll tell me is that the only businesses that work are ones where you can ask somebody to do something for you in exchange for money.

> Next thing you'll tell me is that the only businesses that work are ones where you can ask somebody to do something for you in exchange for money. What other type of business is there?

That is the joke.

Re: Three kinds of AI products work

#32

I’ve been working on a learning / incremental reading tool for a while, and I’ve found LLM and LLM adjacent tech useful, but as ways of resolving ambiguity within a product that doesn’t otherwise show any use of LLM. It’s like LLM-as-parser.

Is there somewhere I can try the tool out? I'm interested in that kind of thing.

Re: Three kinds of AI products work

#33
post #21

Chatbot is the only one I agree with (human in the loop). Agents are essentially the chatbot, but without the human in the loop. Chatbot without human in the loop is a slop factory. Things like "multi-agent systems" are a clever ploy to get you to burn tokens and ideally justify all this madness. Copilot/completion does not work in business terms for me. It looks like it works and it might feel like it's working in s…

Chatbot in many environment simply doesn't work, because we won't let them and if we did, they'd be agents. Here I'm mostly thinking in terms of things like customer service chats. A chatbot that can't reach into other systems are essentially only useful for role playing.

The copilot/completion thing also doesn't work for me. I have no doubt that a lot of developers are having a lot of benefits from the coding LLMs, but I can't make them work.

I think one glaring obvious missing kind of AI is medical image recognition, which is already deployed and working in many scenarios.

Re: Three kinds of AI products work

#34
post #11

The article claims Claude Sonnet 3.5 was released less than 9 months ago, but this is wrong. Claude 3.5 was released in june 2024. Maybe he has been writing this article for a while, maybe he meant Claude Code or Claude 4.0

He meant Sonnet 3.7 which was released on the same day as Claude Code, Feb 24th 2025: https://www.anthropic.com/news/claude-3-7-sonnet

With hindsight, given that Claude Code turned into a billion dollar precut category, it was a bit of a miss bundling those two announcements together like that!

Re: Three kinds of AI products work

#35
> Users simply do not want to type out “hey, can you increase the font size for me” when they could simply hit “ctrl-plus” or click a single button3.

I would def challenge this. “Turn off private relay”, “send this photo to X”, “Add a pit stop at a coffee shop along the way” are all voice commands I would love to use

Re: Three kinds of AI products work

#36

Well, the elephant in the room here is that the generic AI product that is being promised, i.e. "you get into your car in the morning, and on your drive to the office dictate your requirements for one of the apps that is going to guarantee your retirement, in order to find it completely done , rolled out to all the app stores and making money already once you arrive" isn't happening anytime soon, if ever, yet everyon…

The other part to this is that LLMs as a technology definitely has some value as a foundation to build features/products on other than chat bots. But unclear to be whether that value can sustain current valuations.

Is a better de-noisier algorithm in Adobe Lightroom worth $500 billion?

Re: Three kinds of AI products work

#37

Well, the elephant in the room here is that the generic AI product that is being promised, i.e. "you get into your car in the morning, and on your drive to the office dictate your requirements for one of the apps that is going to guarantee your retirement, in order to find it completely done , rolled out to all the app stores and making money already once you arrive" isn't happening anytime soon, if ever, yet everyon…

Skeptics always like to toss in 'if ever' as some form of enlightenment they they are aware of some fundamental limitation of the universe only they are privy to.

Re: Three kinds of AI products work

#38
post #14

>> in five years time most internet users will spend a big part of their day scrolling an AI-generated feed. Yep. Looking forward to the future where you can eat plastic pop-corn while watching the AI-generated video feeds.

Why 5 years, I'm pretty sure we're there today.

Re: Three kinds of AI products work

#39

In my current project the agent (GPT-5) isn't helpful at all. Damn thing, lying all the time to me.

They're idiot savants. Use them for their strengths. Know their weaknesses.

So, what are their strengths then? I've fed it with a detailed, very well documented and typed API description. Asking to construct me some not too hard code snippets based on that. GPT-5 then pretend to do the right thing, but actually is creating meaningless nonsense out of it. Even after I tried to reiterate and refine my tasks. Every junior dev is waaay better.

Re: Three kinds of AI products work

#40
Very obviously missing the mundane agentic work. I think the following things are basically already solved, and are just waiting for the right harness:

- Call this government service center, wait on hold for 45 minutes, then when they finally answer, tell them to reactivate my insurance marketplace account that got wrongly deleted.

- Find a good dentist within 2mi from my house, call them to make sure they take my insurance, and book an appointment sometime in the next two weeks no earlier than 11am

- Figure out how I'm going to get from Baltimore to Boston next Thursday, here's $100 and if you need more, ask me.

- I want to apply a posterizing filter in photoshop, take control of my mouse for the next 10sec and show me where it is in the menu

- Call that gym I never go to and cancel my membership

Post reply on HN