Show HN: Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B

Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by ttul on Saturday August 26, 2023 @10:06AM (#37273072)

Doesn’t this just reflect that humans are generally just large language models? Maybe throw in an extra dimension of “emotions” that are useful for training?

[ Parent | on HN ]

Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by swader999 on Saturday August 26, 2023 @10:25AM (#37273222)

These llms are weak facsimiles of the brain, not humans. The real world is the ultimate training model, it can't be fully substituted with a bunch of strings.

[ Parent | on HN ]

Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by bloaf on Saturday August 26, 2023 @10:34AM (#37273290)

This sounds like the old question "if a blind-from-birth man (who can recognize squares by feel) gained sight would he be able to recognize squares visually?"

And since that question has been answered in the negative, I'm inclined to agree.

[ Parent | on HN ]

Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by slashdev on Saturday August 26, 2023 @12:05PM (#37274032)

Has it been answered in the negative?

[ Parent | on HN ]

Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by bloaf on Saturday August 26, 2023 @03:53PM (#37276240)

https://www.projectprakash.org/_files/ugd/2af8ef_5a0c6250cc3...

[ Parent | on HN ]

Re:Show HN: Beating GPT-4 on HumanEval with a fine-tuned Cod... by goatlover on Saturday August 26, 2023 @03:24PM (#37276005)

No, humans are living organisms. Talking is just one thing we do, and we do it for reasons other than to generate the next token.

[ Parent | on HN ]