# Why emojis suck for reinforcement learning

DevFeed: [Why emojis suck for reinforcement learning](<https://devfeed.tech/articles/why-emojis-suck-for-reinforcement-learning-79699.md>)

Original publisher: [Read original article](<https://coderabbit.ai/blog/why-emojis-suck-for-reinforcement-learning>)

Author: David Loker

Published: 2025-11-07T00:00:00Z

Content type: opinion

Language: en

Sources: [CodeRabbit](<https://devfeed.tech/sources/coderabbit.md>)

Topics: [ai code review](<https://devfeed.tech/topics/ai-code-review.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [rlhf](<https://devfeed.tech/topics/rlhf.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [developer](<https://devfeed.tech/tags/developer.md>), [english](<https://devfeed.tech/tags/english.md>)

## AI overview

The article argues that binary emoji reactions give AI code reviewers too little context and can reward agreeable or low-risk comments over useful review. CodeRabbit describes Learnings, which stores engineers' explanations of team conventions and corrections as instructions for future reviews, linked to repositories and paths. It presents this as a way to adapt reviews to team standards and retain context over time.

## Source excerpt

The simplicity trap Sure, a thumbs up is quick, but is it really teaching your AI reviewer anything useful? Emoji-based feedback feels good, is fast, and universal. On the surface, it even seems to make sense. But code review isn't a light switch. It....