30778d8af8
``` prompt << build_message(bot_user.username, reply) ``` Would store a "cooked" prompt which is invalid, instead just store the raw values which are later passed to build_message Additionally: 1. Disable summary command which needs honing 2. Stop storing decorations (searched for X) in prompt which leads to straying 3. Ship username directly to model, avoiding "user: content" in prompts. This was causing GPT to stray |
||
---|---|---|
.github/workflows | ||
app | ||
assets | ||
config | ||
db | ||
lib | ||
spec | ||
svg-icons | ||
test/javascripts | ||
tokenizers | ||
.discourse-compatibility | ||
.eslintrc | ||
.gitignore | ||
.prettierrc | ||
.rubocop.yml | ||
.streerc | ||
.template-lintrc.js | ||
Gemfile | ||
Gemfile.lock | ||
LICENSE | ||
README.md | ||
package.json | ||
plugin.rb | ||
yarn.lock |
README.md
Plugin Name Plugin
Plugin Summary
For more information, please see: url to meta topic