by doctorpangloss on 10/19/24, 4:01 PM
Yesterday my company changed a single line to switch our application’s LLM backend API from Claude to ChatGPT, because Claude started adding stuff its answers in QA style prompts that it wasn’t before, at least since August 1st.
I wish I could pay for a guarantee of performance, really quantization, which seems so simple but because it can 2-4x decrease their costs, LLM API providers keep quantizing and distilling without telling anyone. It’s a longer journey: to be an enterprise API. Which by the way, is a terrible business to be in.
by mellosouls on 10/19/24, 12:10 PM
This is interesting and appreciated but I'm not sure it's a Show HN unless the OP is representing Anthropic?
by zurfer on 10/19/24, 8:10 AM
Well done. We are building something similar [1] and found that generating UIs (mostly charts) on the fly works surprisingly well in most cases, but can be a bit frustrating if you know exactly what you want and just can't prompt it (as a user) to do that because of some edge case.
While this is a cool demo that shows what LLMs can do I am a bit surprised how polished and advanced it looks (even PDF upload) for a quick start. Anyway I love that it's open source so we can learn from it.
[1] https://getdot.ai
by dash2 on 10/19/24, 10:01 AM
This seems like Anthropic showing people how to build a thin layer around Claude. Can building a thin layer around Claude be a valuable business model? If there are good profitable UIs for Claude, wouldn't Anthropic implement them itself?
by bl4ckneon on 10/19/24, 7:50 AM
(didn't look at the code yet but) Would a challenge of building an app like this that heavily depends on a LLM be getting a deterministic response back? I guess you could code for it to check if it gave you a certain format of data or if it was what you expected, but if I upload something that Claude doesn't understand and it gives back something that breaks the data analysis then that seems it would be tricky to handle that case.
Please correct me if I am wrong. Thanks!
by rerdavies on 10/21/24, 10:19 AM
Kind of fun. I recently used Claude to generate scripts for Gnu Plot, with only slightly less convenience than this. It's kind of spooky what you can ask claude to do. e.g. "Rotate the x-ais labels by 90%; use "Arial Black" for the title, and "Roboto" for the rest of the fonts". Etc.
by Kiro on 10/19/24, 9:38 AM
by weinzierl on 10/19/24, 9:17 AM
I wish they'd focus more on getting the basics solid. Currently Claude can't even render anything beyond the most basic form of a table.
For example, try to let it turn multiple items in a table cell into a bulleted list. It just outputs a mess of literal HTML tags.
by ideashower on 10/19/24, 3:16 PM
Can you take these resulting interactives and export them to publish?
by troupo on 10/19/24, 11:27 AM
Do they have any plans on opening up APIs to private individuals?
by albert_e on 10/19/24, 7:41 AM
Looks very interesting.
I am more familiar with React - am looking for a React example that achieves similar UI, any working examples I can take inspiration from?