Show HN: Interactive Graph by LLM (GPT-4o)
1–10 of 58 posts
Re: Show HN: Interactive Graph by LLM (GPT-4o)
#2This is pretty cool, it's snappy, it seems to work, but there's no way I trust it without a way to check the LLM's work.
Re: Show HN: Interactive Graph by LLM (GPT-4o)
#3Hmmm this doesn't look right? : https://columns.ai/chatgpt/AXoHKTTYYkeT3x
Re: Show HN: Interactive Graph by LLM (GPT-4o)
#4Cute, but can I see sources on the data? I tried some query on some belgian statistics and it gave me just... very weird numbers that i do not trust, but zero way to check them.
Re: Show HN: Interactive Graph by LLM (GPT-4o)
#5This is pretty cool, it's snappy, it seems to work, but there's no way I trust it without a way to check the LLM's work.
Yeah I just tried it with numbers I knew a bit and it seems totally made up. The generated chart showed a linear downwards trend while in reality there isn't one and the numbers seem way off.
Re: Show HN: Interactive Graph by LLM (GPT-4o)
#6Hmmm this doesn't look right? : https://columns.ai/chatgpt/AXoHKTTYYkeT3x
I was surprised, but it does look right https://en.wikipedia.org/wiki/Demographics_of_Ukraine
Re: Show HN: Interactive Graph by LLM (GPT-4o)
#7Re: Show HN: Interactive Graph by LLM (GPT-4o)
#8GDP in Germany for the last 10 years
4k each year but the bar chart goes up
Sounds about right
Re: Show HN: Interactive Graph by LLM (GPT-4o)
#9Would you mind explaining a little more on what is happening in the background?
- What is your core technical value add?
- Do you have the data sets in your own database and you are using OpenAI to query them?
- Looks like you have your own home built database?
- Are you using LLM Agents?
- I saw that you have Airtable integrations, are you able to do the same for any datasource including Airtable?
Re: Show HN: Interactive Graph by LLM (GPT-4o)
#10Hmmm this doesn't look right? : https://columns.ai/chatgpt/AXoHKTTYYkeT3x
I was surprised, but it does look right https://en.wikipedia.org/wiki/Demographics_of_Ukraine
The graph in that page is completely different (e.g. the sharp drop in 2015). This seems to be just linearly interpolating between start and end populations.