Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Three kinds of AI products work

seangoedecke.com

Post reply on HN
Print view View original

71–80 of 130 posts

Re: Three kinds of AI products work

#71

Post by notatoad »

koliber wrote: post #60
notatoad wrote: post #28

Earlier quoted context omitted.

> summarization can you point me to a useful example of this? i see websites including ai-generated summaries all the time, but i've yet to see one that is actually useful and it seems like the product being sold here is simply "ai", not the summary itself - that is, companies and product managers are under pressure to implement some sort of AI, and sticking summaries in places is a way for them to fill that requirem…

I sometimes get contracts, NDAs, or terms and conditions which normally I would automatically accept because they are low stakes and I don't have time to read them. At best I would skim them. Now I pass them through an LLM and ask them to point out interesting, unconventional, or surprising things, and to summarize the document in a few bullet points. They're quite good at this, and I am can use what I discover later…

for your first one, if you're just feeding docs into a chatbot prompt and asking for a summary, i think that matches what the article would call a "chatbot product" rather than a summarization product.

fireflies.ai is interesting though, that's more what i was looking for. i've used the meeting summary tool in google meet before and it was hilariously bad, it's good to hear that there are some companies out there having success with this product type.

Re: Three kinds of AI products work

#72

Post by EagnaIonat »

> This doesn’t work well because savvy users can manipulate the chatbot into calling tools. So you can never give a support chatbot real support powers like “refund this customer”, ...

I would disagree with this.

Part of how security is handled in current agentic systems is to not let the LLM have any access to how the underlying tools work. At best it's like hitting "inspect" in your browser and changing the web page.

Of course, that assumes that the agentic chatbot has been built correctly.

Re: Three kinds of AI products work

#73

Post by echelon »

wongarsu wrote: post #6

This seems to be biased heavily towards products that look like an LLM. And yes, only a small number of those work. But that's because if your product is a thing I chat with, it immediately is in competition with ChatGPT/Claude/Grok/etc, leading to everything the article expressed. But those are hardly the only use cases for LLMs, let alone AI (whatever people nowadays mean by AI) To name some of the obvious counter-…

> One other thing I haven’t mentioned is image generation. Is this part of a chatbot product, or a tool in itself? Frankly, I think AI image generation is still more of a toy than a product, but it’s certainly seeing a ton of use. There’s probably some fertile ground for products here, if they can successfully differentiate themselves from the built-in image generation in ChatGPT.

This guy is so LLM-biased that he's missing the entire media gen ecosystem.

I feel like image, video, music, voice, and 3D generation are a much bigger deal than text. Text and code are mundane compared to rich signals.

These tools are production ready today and can accomplish design, marketing, previz, concept art, game assets, web design, film VFX. It's incredibly useful. As a tool. Today.

Don't sleep on generative media.

Re: Three kinds of AI products work

#74

Post by aunty_helen »

notatoad wrote: post #28
koliber wrote: post #15

A few more seem to work as well, because I've used them and found them valuable - human language translation - summarization - basic content generation - spoken language transcription

> summarization can you point me to a useful example of this? i see websites including ai-generated summaries all the time, but i've yet to see one that is actually useful and it seems like the product being sold here is simply "ai", not the summary itself - that is, companies and product managers are under pressure to implement some sort of AI, and sticking summaries in places is a way for them to fill that requirem…

We built a system that uses summaries of video clips to build a shorts video against a screenplay. Customer was an events company. So think 15 minute wedding highlights video that has all of the important parts to it, bride arrival, ring exchange, kiss the bride, first dance, drunken uncle etc

Re: Three kinds of AI products work

#75

Post by falseprofit »

pixl97 wrote: post #37
ZeroConcerns wrote: post #24

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.

Let’s say there are three options: {soon, later, not at all}. Ruling out only one to arrive at {later, not at all} implies less knowledge than ruling out two and asserting {later}.

Awareness of a fundamental limitation would eliminate possibilities to just {not at all}, and the phrasing would be “never”, rather than “not soon, if ever”.

Re: Three kinds of AI products work

#76

Post by bix6 »

esseph wrote: post #20
bix6 wrote: post #7

On agents it’s interesting but not surprising coding has seen so much initial success. Personally I’m waiting for better O365 and SharePoint agents. I think there’s a lot of automation and helper potential there.

At this point MS should probably sunset SharePoint and try again.

How come?

Re: Three kinds of AI products work

#77

Post by bix6 »

airstrike wrote: post #13
bix6 wrote: post #7

On agents it’s interesting but not surprising coding has seen so much initial success. Personally I’m waiting for better O365 and SharePoint agents. I think there’s a lot of automation and helper potential there.

I'm building an opinionated take on this. It's shaping up nicely. If you're a Rust developer reading this, interested in AI + GUI + Enterprise SaaS, and wants to talk, I'm building a team as we speak. E-mail in profile.

So like an o365 ServiceNow?

Re: Three kinds of AI products work

#78

Post by hencq »

chrisweekly wrote: post #45
websap wrote: post #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

Yes, this! esp the last one. Finding coffee shop / restaurant options ALONG THE WAY seems like it should've been solved years ago. Scenario: while driving, "want to eat in about an hour, must have vegetarian options, don't add more than 10m extra drive time" and get a shortlist to pick from.

Yeah that one is surprisingly difficult even with a Human Intelligence in the passenger seat.

Re: Three kinds of AI products work

#79

Post by samuelknight »

I look at LLMs with an engineering mindset. It is an intelligence black box that goes in a tool box with the old classical algorithms and frameworks. In order to use it in a solution I need to figure out:

1) Whether I can give it information in a compatible and cost effective way

2) Whether the model is likely to to produce useful output

I have use language models for years before LLMs such as part of speech classifiers in the Python NLTK framework.

Re: Three kinds of AI products work

#80

Post by koliber »

gregates wrote: post #69
koliber wrote: post #60

Earlier quoted context omitted.

I sometimes get contracts, NDAs, or terms and conditions which normally I would automatically accept because they are low stakes and I don't have time to read them. At best I would skim them. Now I pass them through an LLM and ask them to point out interesting, unconventional, or surprising things, and to summarize the document in a few bullet points. They're quite good at this, and I am can use what I discover later…

Do you go through the haystack yourself first, find the needle, and then use that to validate your hypothesis that the AI is good at accomplishing that task (because it usually finds the same needle)? If not, how do you know they're good at the task? My own experience using LLMs is that we frequently disagree about which points are crucial and which can be omitted from a summary.

It depends on how much time I have, and how important the task is. I've been surprised and I've been disappointed.

One particular time I was wrestling with a CI/CD issue. I could not for the life of me figure it out. The logs were cryptic and there was a lot of them. In desperation I pasted the 10 or so pages of raw logs into ChatGPT and asked it to see if it can spot the problem. It have me three potential things to look at, and the first one was it.

By directing my attention it saved me a lot of time.

At the same time, I've seen it fail. I recently pasted about 10 meetings worth of conversation notes and asked it to summarize what one person said. It came back with garbage, mixed a bunch of things up, and in general did not come up with anything useful.

In some middle-of-the road cases, what you said mirrors my experience: we disagree what is notable and what is not. Still, this is a net positive. I take the stuff it gives me, discard the things I disagree on, and at least I have a partial summary. I generally check everything it spits out against the original and ask it to cite the original sources, so I don't end up with hallucinated facts. It's less time than writing up a summary myself, and it's the kind of work that I find more enjoyable than typing summaries.

Still, the hit to miss ration is good enough and the time savings on the hits are impressive so I continue to use it in various situations where I need a summary or I need it to direct my attention to something.

Post reply on HN