You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Apparently LLMs might have a general understanding of roughly how much 50 characters is but since there's already a max_tokens defined, I don't think it helps to set a character limit, since it's not gonna result in more exact results than just relying on max_tokens.
Why?
It's not that big of a deal, I just thought it's an, admittedly small, waste of prompt tokens for every commit.
2️⃣ openrouter-commit > aicommits – supports DeepSeek R1, has more AI models, and is more customizable.
Please don't ever do this. People are capable of searching for alternatives on their own, you're just gonna get yourself reported for spam. Please keep issue comments free of spam and advertising, I'm begging you. Even if done in good faith, it's just annoying and adds clutter to the communication
Feature request
Apparently LLMs might have a general understanding of roughly how much 50 characters is but since there's already a
max_tokens
defined, I don't think it helps to set a character limit, since it's not gonna result in more exact results than just relying onmax_tokens
.Why?
It's not that big of a deal, I just thought it's an, admittedly small, waste of prompt tokens for every commit.
Alternatives
No response
Additional context
https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them
Using ShellGPT to test the character count accuracy of GPT 4
The text was updated successfully, but these errors were encountered: