> The entire source code, without tests, is about 15,000 lines, which comes out to about 150,000 tokens with GPT and about 250,000 with Claude.Woah, that big of a difference when it comes to token counting?
Some of the delta is newish:<a href="https://openrouter.ai/blog/insights/opus-47-tokenizer-analysis/" rel="nofollow">https://openrouter.ai/blog/insights/opus-47-tokenizer-analys...
ireadmevs · · focus · HN ↗
Woah, that big of a difference when it comes to token counting?
dnoberon · · focus · HN ↗
roywiggins · · focus · HN ↗
<a href="https://openrouter.ai/blog/insights/opus-47-tokenizer-analysis/" rel="nofollow">https://openrouter.ai/blog/insights/opus-47-tokenizer-analys...