alt Hacker NewsIn 2023 GPT-4 was allegedly 1.8T parameters. In 2026 we have ~100x smaller models (10-20B) that handily outperform it, and can indeed run on a laptop.
Replies
rectang • yesterday at 6:11 PM
How does "outperform" translate to the propensity of an LLM to hallucinate?
➕ show 1 reply
It highly depends on the task. For math and coding, sure. But for knowledge tasks GPT-4 is wayy better than even SOTA ~100B models. For my knowledge test cases the lines get blurry at >400B