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

263 points by surrTurr ↗ HN
There have been many tools powered by GPTs coming out over the past few months. Too many. Which ones are actually worth using?

263 comments

[ 3.1 ms ] story [ 289 ms ] thread
ChatGPT. No point in adding an expensive middleman on top that’s usually just a few clever prompt tricks.

Side note: having gotten access to Copilot Chat, it’s disturbing how quickly the ChatGPT UI has become established in my mind as the standard. Copilot Chat, despite being integrated into VS Code, feels clunky and alien compared to ChatGPT in a separate window. Funny how fast new things become the standard by which others are measured.

Same for me. I think this will only be more true once I am using plugins as standard.
I built a tool that gives GPT a Docker container to run commands in to accomplish a particular task. I find myself using it for things like simple file conversions (it mounts the current working directory into the container). It can install software in the container so it’s like a chatbot with the entire apt universe at its disposal.

https://github.com/drifting-in-space/botsh

wow that's a really useful little sandbox. Definitely will play with this later
The Playground tool for ChatGPT 4 in the API documentation site.

It's like ChatGPT but gives you the option to change / edit and rerun prompts more effectively.

Please, the title is a bit misleading. GPT can be many things, including "General Purpose Technology". The post is about the product ChatGPT.

https://en.wikipedia.org/wiki/General-purpose_technology

I don't see a point to fighting against the current, it begs the question: what could possibly be achieved?
(comment deleted)
I think it's OK for there to be multiple definitions for a TLA (Three Letter Acronym, but also Tennessee Library Association, Temporal Logic of Actions and quite a few others.)

I had genuinely never seen GPT used for General Purpose Technology until I followed your link to Wikipedia.

There are so many useful tools, that I keep an Awesome list up to date with openAI API, as well as open LLM tools. Especially the up to date list of open LLM models might be of interest to some, in case someone wants to be independent of OpenAI:

https://github.com/underlines/awesome-marketing-datascience/...

I like the list, but the list name itself might be better!
I don't like those lists... too much things. No idea what is actually usable / usefull in there.
Raycast AI (now Raycast Pro). It makes using GPT more accessible and user-friendly by bringing it right to where you need it. Also their take on AI Commands is quite useful. You can create commands with a custom prompt and the prompt will additionally contain the currently selected text.

Some example AI commands that are built in (you can of course create your own commands): - Improve Writing - Change Tone to Friendly / Confident / Professional / Casual - Fix Spelling and Grammar - Find Bugs in Code - Explain Code Step by Step - Explain This in Simple Terms

https://www.raycast.com/pro

Downside is that you can't select GPT4 for now - probably because users would associate the slowness with Raycast then.
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/

+10 for phind. It's the only GPT tool I find that works well - for me currently.
For me, the beauty of Phind is that it will wade through the ad ridden web 3.0 hellscape to get an answer for me in plain text. I am not sure exactly how much of that process is to do with the language model per se. Probably basic vector store distance measures and traditional indexing paired with text extraction would do the job "just as well". I don't really need the natural language spin on top (I think).
Yeah, Phind has replaced Google for half of my searches. My only small complaint is reliability — occasionally I get “inference service not available” (paraphrased) and have to regenerate once or more.
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 cool, but kinda feeling like the worse version of each.. if that makes sense.

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.
I was instantly a big believer in Phind.

It has replaced 95% of my previous DuckDuckGo searches for development info.

I even used it with another developer to solve a mission critical bug based on some very vague symptoms. It's saved so much time, I'll never go back.

Yeah Phind is the only AI service I use on a daily basis. Plus, free access to GPT-4 in answers is a bonus. They really nailed the experience
I've used it many times for things that aren't technical. It's fantastic. I love that it provides references.
link to the docs and tell it, it's wrong about version, or ask for the features of something like nextjs 3.4 and it'll refresh it's context and give much better results. I don't know what their secret sauce is but it blows bing out of the water.
Phind is one of the stickiest apps I’ve ever used, reminds me of when I first used Google Images… now I use it constantly

It also seems much more useful than ChatGPT or StackOverflow by themselves

I am more than a bit biased, but Heuristi.ca is my favorite tool for knowledge exploration using a mind-map like layout that uses the ChatGPT API.

http://heuristi.ca/

For GPT/Copilot style help for pandas, in notebooks REPL flow (without needing to install plugins), I built sketch. I genuinely use it every-time I'm working on pandas dataframes for a quick one-off analysis. Just makes the iteration loop so much faster. (Specifically the `.sketch.howto`, anecdotally I actually don't use `.sketch.ask` anymore)

https://github.com/approximatelabs/sketch

News Minimalist:

> It uses AI (ChatGPT-4) to read the top 1000 news every day and rank them by significance on a scale from 0 to 10 based on event magnitude, scale, potential, and source credibility.

https://www.newsminimalist.com/

Most of the articles in top 10 seem to be about Ukraine. I understand the war is significant, but 5 articles in Top 10 ?

3 articles in Top 20 about Israel ?

They should work on how exactly is the significance determined, and significant for whom ?

Significance is obviously subjective, but you can definitely make an argument that "major world power is trying to take over a country" is significant. It's been going on for a while which makes it harder to feel like it's so important, but it really is.
Hey, author here.

That was the initial idea. Significant events don't stop being significant once we get tired of hearing about them.

But there's definitely a problem of duplicates. When separate news sites post about a similar event it get rated relatively similar by ChatGPT, which creates clusters like we see today.

I want to solve this soon by combining similar stories into single block with one title.

That's another problem I had noticed from a bit of a play (similar problem with boringreport), so I'm glad you're already on it! I've signed up for premium.
Author here. I plan to add a "how it works" section, but the basic idea is that each news story is rated on several parameters:

- scale is the number of people affected by the event described in the news story. - magnitude is the strength of the effect. - potential is the likeliness of the event to lead to other, more significant events. - source credibility considers how trustworthy is the source, and what is its track record.

Then these parameters are combined into a single score.

Also fair criticism re: repeats. I plan to solve this by clustering similar news, so one event is only given one title.

We are building a programming language (https://lmql.ai), that allows you to execute programs with control-flow and constrained behavior on top of LLMs. Essentially imperative LLM text generation.
How does this compare to Guidance?
Not sure if it's GPT-powered, but I now get all my news from http://newsminimalist.com

It's so calm and to the point, I'm never going back to anything else.

Interesting. Is there a way to shape it to topics you care about? It's all about Sudan and Ukraine, which while globally important I'm much more interested in local (Australian) news / tech news.
I'm not a paid user (yet?), but it seems on the pricing page that you can pay $10/mo for shaping topics to your prefs.
Hey, author here.

Yeah, the initial idea was to uncover globally significant news, but a lot of people are asking for ways to find "locally important" or "industry important" news. So I'm shifting my direction a little bit.

It's currently possible to filter news by broad category in a paid version (health, science, tech). I plan to expand the list of categories, so it's possible to go deeper. I also plan to add news in other languages (translated) and add country filters, so it's possible to see only news related to individual country/region.

Thanks for building this! One thing I'd love is for there to be fewer duplicates.

The top 6 stories at the moment are duplicates of a single story:

7.7 - Russia launches intense air attack on Kyiv, Ukraine claims to have shot down all 18 missiles.

7.1 - Series of explosions heard in Kyiv as Russia attacks.

7.1 - Massive Russian missile strike hits Kyiv in attempt to destroy Ukraine's new air defence systems.

6.9 - Kyiv targeted by dense Russian missile and drone attack.

6.9 - Russian drones and ballistic missiles attack Ukraine's capital after President Zelensky secures new arms pledges.

6.9 - Russia launches intense air attack on Kyiv with drones, cruise missiles, and possible ballistic missiles.

> It uses AI (ChatGPT-4) to read the top 1000 news every day and rank them by significance on a scale from 0 to 10 based on event magnitude, scale, potential, and source credibility.
[flagged]
You're using a language model to give retail investors that don't know any better financial advice? This is a horrendous idea that will probably get you sued if you act like it's an investment strategy. Financial advice, like legal advice, is not something you can trust an AI to give out as if it's complete advice. There's a reason you need a license for this.
Oh wow. Every sentence in your comment just makes it progressively worse.

What you’re creating is outright dangerous if not actively malicious. You’re targeting inexperienced retail investors, and giving them financial advice that you’ve pulled out of an LLMs arse.

Somebody is going to get hurt, and you are without going to get sued over it. It’s not an if, but when.

EDIT: s/ u/ i/

I’m sure they have a ‘this is not financial advice’ notice, which is likely to be about as effective as those offered by the finfluencers currently being targeted by the Australian Tax Office.
I'd have a bit more (still not much) sympathy for them if they hadn't said they're actively targeting inexperienced investors. That's just inevitably going to fuck someone over. And yeah, a notice like that is about as valid as a warranty-void-if-removed sticker.

I took a look at their site, and it seems like they're pushing NFTs as well, and although their site doesn't seem to mention blockchain, their investor pitch deck does seem to. So many red flags.

It's times like these I think that maybe software engineers should need to be professionally licensed.

I'll try for some more constructive input: This is a good idea, if you properly couch it. Just as an investor must understand they can lose money when investing, they must understand this sort of input won't always be entirely accurate (much like the evaluation by a real human wouldn't be). A well informed human being gets their information from many sources.

If you can manage to get your users to actually understand this, I think this is a very cool idea. Following a giant stream of news about your big stocks is tedious as hell and anything that can reduce that workload is a good idea.

> A well informed human being gets their information from many sources

They're actively targeting uninformed, inexperienced investors though.

Yes, and the way to solve them having no info is to give them an easy start and guide them to next steps they can actually work with. In my opinion it is not useful to take a service that seeks to solve something and bury them in "you will get sued" comments. It's hateful and won't lead anywhere good.
I don't care how "hateful" I'm being. Making a LLM do stock picks and then telling people who don't know any better that it's a reliable way to invest money is something that will cause someone to lose their savings. It's not just about them getting sued - it's about them causing gigantic harm to someone's actual life. Plus, if you take a look at their site, it's clear they're also involved with web3/crypto nonsense, which has stolen quite enough money from honest people already.
I’m being blunt, not hateful. Not everything needs to be wrapped in nice words and pleasantries for the sake of it.

I find it hard to be constructive toward a project that I strongly feel should not exist and whose existence I believe will be actively harmful.

MirrorThink is able to search and read scientific papers to answer serious scientific questions and find solutions to deep engineering problems.

It is also GPT-4 for free (for now).

https://mirrorthink.ai/

Too bad the sign up process is broken. I get to the last step to verify and the button presses and nothing happens.
You should have gotten an email with the verification code. There's a spike in sign-ups right now so it fails occasionally, try a few times, it'll work.
fyi, he self-identified as GPT-3, and did not seem to be "aware" that he was specialized in science, but in "a wide range of topics".

Edit: and I strongly suggest you create a "Delete your account" page or at least a way to contact the person responsible to do it :).

There's not a even a logout button yet :) Noted, you are right.

Yes interestingly GPT-4 identifies as GPT-3, and you need to be quite explicit about asking it to search for the answer in papers (see collapsed prompt).

But it is excellent at using the content of papers to ground itself, it is really hard to make it hallucinate or provide evidence for scientifically incorrect claims. And it is so much faster than searching for whole papers and reading through them.

We are focusing on the core value of giving it access to scientific knowledge right now, but we are working hard to mature everything surrounding it too.

I tried with a few papers. Didn't work. Always making up summaries.