Show HN: How I Topped the HuggingFace Open LLM Leaderboard on Two Gaming GPUs

Re:Show HN: How I Topped the HuggingFace Open LLM Leaderboar... by dormento on Tuesday March 10, 2026 @01:36PM (#47326369)

For all we know, AI tech companies could theoretically have converted all of the "acquired" (ahem!) training set material into base64 and used it for training as well, just like you would encode say japanese romaji or hebrew written in the english alphabet.

[ Parent | on HN ]

Re:Show HN: How I Topped the HuggingFace Open LLM Leaderboar... by dtj1123 on Tuesday March 10, 2026 @02:18PM (#47326900)

Unlikely that every company would have bothered to do this.

[ Parent | on HN ]

Re:Show HN: How I Topped the HuggingFace Open LLM Leaderboar... by idiotsecant on Tuesday March 10, 2026 @03:00PM (#47327461)

'Yes, I know we already trained on all that data, but now I want you to convert to base64 and train it again! at enormous cost!'

[ Parent | on HN ]

Re:Show HN: How I Topped the HuggingFace Open LLM Leaderboar... by adcoleman6 on Wednesday March 11, 2026 @08:34AM (#47334754)

On the contrary, it could be a deliberate attempt to augment or diversify the dataset.

[ Parent | on HN ]