←back to thread

GPT-4 and professional benchmarks: the wrong answer to the wrong question

(aisnakeoil.substack.com)
340 points agomez314 | 1 comments | 21 Mar 23 13:12 UTC | HN request time: 0.206s | source
Show context
madsbuch ◴[21 Mar 23 13:43 UTC] No.35245982[source]▶
It seems like many people focus on reasoning capabilities of the GPT models.

The me the real value is in the industrial scale pattern recognition capabilities. I can indicate something I vaguely know or ask it to expand on a concept for further research.

Within the last hours I have used it to kick-start my research on the AT1 bond and why Credit Suisse let them default and it helped me recall that it was the GenServer pattern I was looking for in Elixir when you have a facade that calls to an independent process.

replies(3): >>35246019 #>>35246275 #>>35247434 #
1. rmckayfleming ◴[21 Mar 23 15:16 UTC] No.35247434[source]▶
Yep, it's saved me a lot of time on data transformation tasks. For instance, I wanted to convert the colors in Tailwind to CSS variables. I had the JSON listing all of the names and hex colors, I just needed to rewrite the names and convert the hex to base 10. A rather straightforward mapping, but I'd need to write the function for it. I just asked ChatGPT to give me the function. I read the function, it looked good. Boom, done in less than a minute. What's funny is that ChatGPT started spitting out the expected output of the function. And it was right! Perhaps surprising on the face of it, but really it's a simple pattern mapping.