Comment by Der_Einzige
9 hours ago
That’s anthropic fault for continuing to use top-K, a stoneage tier shitty sampler. Your own head of mechanistic interpretability invented a better one called tail free sampling in 2019.
9 hours ago
That’s anthropic fault for continuing to use top-K, a stoneage tier shitty sampler. Your own head of mechanistic interpretability invented a better one called tail free sampling in 2019.
That seems to have nice properties, but 2019 was a while ago. Is the problem of top-k sampling still relevant with much better frontier models?