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

CustomGPT

customgpt.ai

Post reply on HN
Print view View original

21–30 of 33 posts

Re: CustomGPT

#21

Post by geepytee »

LeoPanthera wrote: post #11
gecersiznick wrote: post #7

Does anyone have any pointers as to how I can train ChatGPT on my personal corpus and create my own personal assistant?

Just shove all your information in the prompt. I assume that's what these guys are doing anyway. ChatGPT doesn't yet have any API, but you can use text-davinci-003, which does have an API and is functionally identical. The API costs for a large prompt are quite high, and since you have to repeat it with every single query, your costs can go up very quickly.

davinci-003 has a 4k tokens cap, you cannot just 'shove all your information in the prompt.' Can parallelize but then rate limits become a problem. Really curious to hear how these guys are handling it.

Re: CustomGPT

#22

Post by foverzar »

humanistbot wrote: post #14

Am I too harsh for expecting that in 2023, a company actively signing up customers for a cloud-based service should have enough autoscaling so that getting to the front page of HN doesn't overload the landing page? It just doesn't give me much faith that the actual product will be stable enough to use. Especially just giving a generic 5XX error from nginx is a bad sign. Edit: did this get manually knocked off the fro…

I feel like it's only the part with generic nginx 5xx error that sets the bar a bit too high. Too many huge services suffer from the same sin.

Re: CustomGPT

#23

Post by Deukhoofd »

humanistbot wrote: post #14

Am I too harsh for expecting that in 2023, a company actively signing up customers for a cloud-based service should have enough autoscaling so that getting to the front page of HN doesn't overload the landing page? It just doesn't give me much faith that the actual product will be stable enough to use. Especially just giving a generic 5XX error from nginx is a bad sign. Edit: did this get manually knocked off the fro…

Let's be fair, ChatGPT has had issues with being overloaded ever since its initial release, and they're still not entirely fixed.

Re: CustomGPT

#24

Post by AvAn12 »

humanistbot wrote: post #14

Am I too harsh for expecting that in 2023, a company actively signing up customers for a cloud-based service should have enough autoscaling so that getting to the front page of HN doesn't overload the landing page? It just doesn't give me much faith that the actual product will be stable enough to use. Especially just giving a generic 5XX error from nginx is a bad sign. Edit: did this get manually knocked off the fro…

Or could this be a marketing stunt? OMG we are so popular that nobody can get to our site for the first 48 hours etc. etc.

Re: CustomGPT

#25

Post by voytec »

Deukhoofd wrote: post #23
humanistbot wrote: post #14

Am I too harsh for expecting that in 2023, a company actively signing up customers for a cloud-based service should have enough autoscaling so that getting to the front page of HN doesn't overload the landing page? It just doesn't give me much faith that the actual product will be stable enough to use. Especially just giving a generic 5XX error from nginx is a bad sign. Edit: did this get manually knocked off the fro…

Let's be fair, ChatGPT has had issues with being overloaded ever since its initial release, and they're still not entirely fixed.

ChatGPT may need a tad stronger infrastructure than a landing page.

Re: CustomGPT

#26

Post by folli »

paxys wrote: post #8

Founders really need to start doing 10 minutes of due diligence to ensure that their sites won't crash and burn under moderate Hacker News or Product Hunt traffic before posting at these places. You get one shot at front page success, and are now losing valuable impressions because people can't even open your website. And you not being able to keep a marketing page up and running doesn't really give me confidence in…

There's a very slim chance of hitting the front page on HN (believe me, look at my post history, I tried a couple of times), do you prepare for such an unlikely event...

I mean if course you should, because otherwise why post on HN, but if it's 'just' a side project, I understand why you don't want to spend time configuring Cloudflare.

Re: CustomGPT

#27

Post by KidComputer »

geepytee wrote: post #21
LeoPanthera wrote: post #11

Earlier quoted context omitted.

Just shove all your information in the prompt. I assume that's what these guys are doing anyway. ChatGPT doesn't yet have any API, but you can use text-davinci-003, which does have an API and is functionally identical. The API costs for a large prompt are quite high, and since you have to repeat it with every single query, your costs can go up very quickly.

davinci-003 has a 4k tokens cap, you cannot just 'shove all your information in the prompt.' Can parallelize but then rate limits become a problem. Really curious to hear how these guys are handling it.

You shove the whole corpus in a vector db using embeddings, query the nearest neighbors to an input and inject those into a prompt to pass to GPT.

https://langchain.readthedocs.io/en/latest/modules/chains/co...

Re: CustomGPT

#28

Post by elicash »

gecersiznick wrote: post #7

Does anyone have any pointers as to how I can train ChatGPT on my personal corpus and create my own personal assistant?

It's insanely easy to use RelevanceAI to upload a 1-column spreadsheet, click the "vectorize" button, and then have something working. The problem is putting the data into that spreadsheet.

https://relevanceai.com/blog/use-all-of-your-blog-posts-and-...

As far as the next step...

Google allows you to export your email data. Ideally, you could download that data and upload it to a service that looked at original messages and your replies (and replies to replies) and trained on that file without having to make sense of what Google gives you.

If that was working, then you could have it reply to emails for you.

Re: CustomGPT

#29

Post by humanistbot »

Deukhoofd wrote: post #23
humanistbot wrote: post #14

Am I too harsh for expecting that in 2023, a company actively signing up customers for a cloud-based service should have enough autoscaling so that getting to the front page of HN doesn't overload the landing page? It just doesn't give me much faith that the actual product will be stable enough to use. Especially just giving a generic 5XX error from nginx is a bad sign. Edit: did this get manually knocked off the fro…

Let's be fair, ChatGPT has had issues with being overloaded ever since its initial release, and they're still not entirely fixed.

Sure, but their landing page never goes down when ChatGPT is over capacity, and their over capacity page is a delight of downtime design. It has auto-generated content in different genre styles about being over capacity. They even let you enter your email to get notified when it is back. But I do get frustrated that every time I've entered my email to be notified I've never actually been notified.

Re: CustomGPT

#30

Post by gecersiznick »

mmaia wrote: post #18
gecersiznick wrote: post #7

Does anyone have any pointers as to how I can train ChatGPT on my personal corpus and create my own personal assistant?

Check OpeanAI's tutorials [1] and cookbook [2]. Or try LangChain [3], which abstracts a lot of the work. [1] - https://platform.openai.com/docs/tutorials [2] - https://github.com/openai/openai-cookbook [3] - https://github.com/hwchase17/langchain

This is great. Thanks!
Post reply on HN