 |
| Don Knuth Plays with ChatGPT (cs.stanford.edu) | ||
| recommended by 2 users | 2023 | 32 points by talonx | llm internals | original thread | | ||
| 2 users recommended this thread. What they said: |
| nhubbard May 21, 2023 | on: Don Knuth Plays with ChatGPT, in Context | context |
|
heyzk May 22, 2023 | on: Knuth Optimystic Benchmark | context
Hey all, I found the post about Don Knuth and ChatGPT [1] very interesting so I hacked together this project over the weekend. Optimystic periodically re-runs Knuth's questions against the latest GPT model (additionally I've asked GPT to score the updated answers as PASS/FAIL). Initially I thought it would just be a fun thing, but I've realized there could be some value to the larger LLM community. Also I think it would be interesting to apply this format to experts in other fields. Appreciate any feedback. |
Hi HN,
I saw the interesting message posted yesterday where Don Knuth played with ChatGPT in a discussion with Stephen Wolfram [0]. However, the way the message was formatted, I found it very difficult to constantly scroll up and down reading the questions, responses, and discussion in separate sections. I reformatted the message, with extremely minimal editing (like replacing "chatGPT" with "ChatGPT" because I'm a bit of a pedant, or changing "Answer #x" in the discussion section to "This answer"), to make it easier to read, and wanted to share it with everyone else.
[0]: https://news.ycombinator.com/item?id=36012360