Comment by longnguyen | Hacker News Reader

Comment by longnguyen | Hacker News Reader

I didn't use Bing much but in my experience, it's a lot harder to achieve what I want. For example, it almost always search the web for an answer which is a hit or miss for me.

If you want to use GPTs or to generate images with Dall-E then ChatGPT Plus is a no brainer I guess.

But if your focus is on GPT-4 then I highly recommend to use an API instead.

There are multiple pros of using an API Key:

- You pay for your usages. I've been using API Key exclusively and most of the time, it cost me around $5-$10 a month

- Your data is not used for training. This is important for a privacy-minded user like me. Though you can disable this in ChatGPT (but you will lose chat history)

- No message limit. Though there are rate limits to prevent abuse but generally, you do not have the message limit like the ChatGPT

- You can choose previous GPT models. In my experience, `gpt-4-0314` was the peak gpt-4 model.

Depends on the applications, you can also get these:

- Access to multiple AI services: OpenAI, Azure or OpenRouter

- Build custom AI workflows

- Voice search & text-to-speech etc.

- Deeper integrations with other apps & services

There are also a few cons:

- No GPTs support yet

- If you use Dall E a lot then ChatGPT plus is more affordable. Generating images using Dall E API can be quite expensive

Edit: Some tips when using an API Key:

- You pay for tokens used (basically how long your question & AI's answers). The price per chat message is not expensive, but usually you will need to send the whole conversation to OpenAI, which makes it expensive. Make sure to pick an app that allows you to limit the chat context.

- Don't use GPT-4 for tasks that doesn't require deeper reasoning capabilities. I find that GPT-3.5 turbo is still very good at simple tasks like: grammar fixes, improve your writing, translations ...

- Use different system prompts for different tasks: for example, I have a special prompt for coding tasks, and a different system prompt for writing tasks. It usually give a much better result.

Shameless plug: I've been building a native ChatGPT app for Mac called BoltAI[0], give it a try

[0]: https://boltai.com

This is the way - I just had chatgpt make me a personal use command line utility that just uses the API to mimic chatgpt with whatever model you pass in, saves the running chat as a text file, and gives you a running cost with every prompt. It took about an hour to get something I was happy with, but now I average about a buck a month on it (but I still use the free chatgpt/claude for simpler queries)

I think your section on data privacy could mislead some folks. You’ve written:

> Is my data protected? Absolutely. BoltAI operates locally on your device, and no user input or prompts are stored or sent to us.

While the explanation might be true, as far as I understand it, you can’t assert that users’ data is “absolutely” protected, because it fundamentally depends on OpenAI to keep your users’ data safe too, which you can’t control.

I would guess most of your audience would understand this anyway, but I would be careful as potentially someone could sue you in case OpenAI had a data breach or something.

I think you're right. Thanks for the feedback. I will update it soon!

> But if your focus is on GPT-4 then I highly recommend to use an API instead.

When you have made that choice is it still possible to use 'browse the web' or 'talk to a PDF' like functionality? If so, what would be the best way to do it?

It depends a lot on the GPT client (third-party application).

My app (BoltAI) does support web search (via Google Search) and web browsing (built-in) but not chat w/ PDF functionality.

I built another app[0] specifically for that use case.

So I guess if you need an all-in-one kind of functionality then ChatGPT could be a better choice.

[0]: https://pdfpals.com

I'm a big fan of TypingMind as a front end. typingmind.com

Haha yeah, same. TypingMind is probably the client with the most features. Tony ships at a crazy speed. With BoltAI, I want to focus on MacOS with more native integrations.

Heh, yeah, he is a crazy coder no doubt. Good to have a Mac specific option though. Good luck with it.

>> In my experience, `gpt-4-0314` was the peak gpt-4 model.

That's interesting. Why do you say that? And where can we access the model from?

It’s just my personal experience. So I mostly use GPT-4 for coding tasks and gpt-4-0314 usually gives me the answer I want, without having to use system prompt tricks like this https://twitter.com/voooooogel/status/1730726744314069190

If you use API Key then you can change the model parameter. Here is the list of models that OpenAI support: https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turb...

Too bad it’s considered legacy model and will be deprecated next year.

Is there a relationship between MindMac, which I have seen before on HN, and BoltAI? Websites are quite similar.

No, there isn't. If you're talking about the design then I can see both were modified from a paid Tailwind UI template. For marketing copy, all I can say is they were "inspired" by mine. You can easily check using Wayback Machine [0][1] :D

[0]: https://web.archive.org/web/20230522013022/https://boltai.ap...

[1]: https://web.archive.org/web/20230711214004/https://mindmac.a...

kudos for perpetual license. app looks neat. non-techy question: how do you ensure users their keys are safe?

Thanks. By default, BoltAI stores user's API key in Apple Keychain. So other applications and scripts won't be able to access this key without triggering the OS's security dialog.

Secondly, all requests are sent directly to OpenAI servers. There is absolutely no middle/proxy server.

There is however a proxy server for Claude but this was due to a technical difficulty and user can host their own proxy server instead.

thank you for the clear explanation

It is not a perpetual license. "One year of free updates included." means subscription. Especially considering product depends on third party API, which rapidly evolves, you cannot really stick with the old version, because some new model will not be embedded in the one year old version of the app you have. So, in reality you pay $40-80 a year for this product. Plus your ChatGPT API Key usage. In that case I would just suggest pay for the OpenAI.

If you are looking for an alternative of the app for the ChatGPT - I would suggest https://www.typingmind.com I have been using it since it was released. It is also available with Setapp subscription, which gives you some free usage of the OpenAI with Setapp embedded API key.

Technically it's perpetual fallback license, which was popularized by the Jetbrain team [0]

> A perpetual fallback license is a license that allows you to use a specific version of software without an active subscription for it. The license also includes all bugfix updates, more specifically in X.Y.Z version all Z releases are included.

After 1 year, you can continue to use the app without having to upgrade. You won't receive new features, but will continue to receive bug fixes for the features released previously.

So I can argue it's not "subscription".

Plus, renewal cost 50% less, so it's not $40-$80 a year, but only $20-$40 a year after the first year.

And lastly, the app fetch model lists from OpenAI API so there is no need to "support new models".

I believe this is a sustainable pricing model for an indie developer like me. And I believe it's fair for everyone.

[0]: https://sales.jetbrains.com/hc/en-gb/articles/207240845-What...

I feel like if you have to specify “technically”, you agree with me that it is basically a subscription.

As an Indie developer myself I do not support subscription based licensing (or your version of license) for B2C products. You can offer B2B subscription based licensing, but B2C should always be perpetual licenses. Sure it is ok to ask for the upgrade to new version, which has significant features.

And to clarify, we are talking about the product that does not have any outgoing server spending.

That is my opinion.

> I feel like if you have to specify “technically”, you agree with me that it is basically a subscription.

No, I am not. The "technical" part here is the "fallback" in "perpetual fallback license".

Appreciate your opinion and I'm sure many think the same way.

But selling perpetual licenses just won't work for me. It's not sustainable, especially for this kind of app.

that's no different than pay the full price for new version that comes out every year. do you remember how perpetual licenses use to work?

I feel like Sublime Text showed the best of it. You purchase the new license every new major version. Affinity apps are the same. Acorn. Alfred. And a lot more. There are certainly some apps that release a major update every year. But in that case you pay for work already done. In case if you pay for subscription, you are going to see minor updates “bug fixes”.

I don’t see a reason for an indie developer to charge subscription, if there is no server cost. New versions should just make the app interesting for more users, so the income should be flowing constantly every month.

Anyway, I just personally don’t support subscription based apps and never will.

Reply on news.ycombinator.com