Live data from Hacker News

Ask HN: What's your favorite GPT powered tool?

news.ycombinator.com

211–220 of 266 posts

Re: Ask HN: What's your favorite GPT powered tool?

#211
post #113

For me, in terms of ones I’ve used 10 times or more during the past week: Chatgpt An iPhone app to use gpt-4 An ai newsletter that sends me new tools (I’ve found lots of cool tools from it but none that I use regularly) I think that’s it? Kinda surprising. There are so many gpt powered products I’ve tried but none I’ve stuck with.

Dude!! URLs please.

I run this newsletter on things like business ideas, app launches, langchain deep dives, and other ai newsworthy things: https://curl.beehiiv.com

Re: Ask HN: What's your favorite GPT powered tool?

#213
post #73

Am I the only one who isn't using ChatGPT on a regular basis? Though I've made a few attempts to use it, generally I already know the answers to most trivial questions. And by going into more complex questions and scenarios, it becomes apparent that ChatGPT lacks a deep understanding of the suggestions it provides. It turns out to be a pretty frustrating experience. Also I've noticed that by the time I've crafted int…

[dead]

Re: Ask HN: What's your favorite GPT powered tool?

#214
post #73

Am I the only one who isn't using ChatGPT on a regular basis? Though I've made a few attempts to use it, generally I already know the answers to most trivial questions. And by going into more complex questions and scenarios, it becomes apparent that ChatGPT lacks a deep understanding of the suggestions it provides. It turns out to be a pretty frustrating experience. Also I've noticed that by the time I've crafted int…

This is almost the same thing I say to people. To ask GPT about something and be able to determine whether its answer is false or not, you already need to be competent and knowledgeable in that topic. If you're already competent and knowledgeable in a topic, you don't need to ask GPT about it because you already know it. ChatGPT is not an expert, it's not even written to try to be one, it's fancy phone keyboard predi…

GPT-4 is decent [1] at generating SQL queries from a short text description.

[1] assuming you write raw SQL rarely if ever by hand

Re: Ask HN: What's your favorite GPT powered tool?

#215

Havana summarizes my sales calls and drafts a follow-up email automatically after each call. https://tryhavana.com When you do more than 5-10 sales calls a week, writing up notes and emails can take hours of your time. It's tedious work but also must be done (otherwise you might forget what's going on in a deal when it's time to do another call down the line!). Also, the quality of the summaries and emails must be go…

Can vouch for Havana. We use fathom for video recording but the AI summaries are unusable. Havana has filled that gap

Re: Ask HN: What's your favorite GPT powered tool?

#216
post #14

Phind is a GPT powered search engine optimized for developers / technical documentation. It searches the web and tries to aggregate results from multiple web sites. Although there are instances where it references outdated versions of libraries, on balance, it significantly reduced my time spent on technical research. https://www.phind.com/

I wish Phind would "autoGPT" a bit more, though. It often feels like Phind just grabs the top X results and makes a reply from those. If i was searching and those results came up i'd often skip them. Strangely i use ChatGPT4 every day but am using Phind less and less. When i have something to search the web for, Kagi is faster for me. When i want to search GPT4 (thoughts/whatever) ChatGPT is faster for me. Phind is c…

It doesn't just pick the top result though. I was given an answer from SO that wasn't the top voted and not the "approved" answer, either. But it was, imo, the best answer it could've given me. I was pleasantly surprised.

Re: Ask HN: What's your favorite GPT powered tool?

#218
post #73

Am I the only one who isn't using ChatGPT on a regular basis? Though I've made a few attempts to use it, generally I already know the answers to most trivial questions. And by going into more complex questions and scenarios, it becomes apparent that ChatGPT lacks a deep understanding of the suggestions it provides. It turns out to be a pretty frustrating experience. Also I've noticed that by the time I've crafted int…

One mistake I've seen people who are unhappy with GPT make is they ask it questions they already know the answer to, topics they are an expert in, and then tear down the response. Try asking it things you would google for. I'm finding it to be a pretty good "I'd like an answer to this question, I don't want to wade through a bunch of google results trying to find the one that answers this question" engine. Sometimes…

> gives reference links, which ChatGPT can't do

Yes it can, you just have to specifiy that it do so.

I find that it tends to limit the hallucination, or hilights when it's hallucinating.

Re: Ask HN: What's your favorite GPT powered tool?

#219

Earlier quoted context omitted.

One mistake I've seen people who are unhappy with GPT make is they ask it questions they already know the answer to, topics they are an expert in, and then tear down the response. Try asking it things you would google for. I'm finding it to be a pretty good "I'd like an answer to this question, I don't want to wade through a bunch of google results trying to find the one that answers this question" engine. Sometimes…

> gives reference links, which ChatGPT can't do Yes it can, you just have to specifiy that it do so. I find that it tends to limit the hallucination, or hilights when it's hallucinating.

I haven't had much luck with that. The most recent example I'm thinking of, with ChatGPT 4, is I asked it a question and it's response included something like "can be set up by following the documentation". I asked "What is the URL of the documentation you refer to above" and it said "I'm a LLM, I can't do that."

Re: Ask HN: What's your favorite GPT powered tool?

#220
post #115

Earlier quoted context omitted.

It’s very important to qualify this with which model you are using. 3.5 and 4 are very different in the quality of answers they give, the version numbering is deceptive. As a side note, although I can’t confirm this it seems like the general quality of answers for both 3.5 and 4 decreased over time. I suspect they are doing further RLHF which has shown to make the model stupider for lack of a better word.

Using 3.5

There is a trick to get better performance out of 3.5, examples specifically in Q&A format. You basically have to show it how you want it to act first and then ask your question or whatever. It can be a pain to craft a good prompt but the really important and amazing thing is that the knowledge it gains from the examples is transferable to other similar tasks! So you don’t have to answer your own question, just show it how you prefer questions to be answered and then ask the question you want the answer to (or tell it to perform the task you want it to) and you can reuse the prompt for other questions.
Post reply on HN