---
title: "Discussion on \"When Confidence Becomes Overconfidence\" | Hashnode"
description: "Discussion on \"When Confidence Becomes Overconfidence\". Calibration Collapse After RLHF; and How to Fix It Without Retraining\nReinforcement Learning from Human Feedback makes language models more helpful and less harmful. It also makes them systematically"
url: "https://hashnode.com/posts/when-confidence-becomes-overconfidence/6a0df68e8b034602219ffb98"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [When Confidence Becomes Overconfidence](https://okonu.hashnode.dev/when-confidence-becomes-overconfidence?utm_source=hashnode&utm_medium=feed)

Calibration Collapse After RLHF; and How to Fix It Without Retraining Reinforcement Learning from Human Feedback makes language models more helpful and less harmful. It also makes them systematically

May 2 · 11 min read · okonu.hashnode.dev  
Read the article

## Written by

[Ian Okonu](https://hashnode.com/@Okonu)

@Okonu · Nairobi, Kenya

  
[View profile](https://hashnode.com/@Okonu)

ML &AI Architect

LLM Orchestration · RAG Pipelines · Multi-Agent Systems | Production AI for Fintech, Legal &amp; Gov on Azure · GCP · AWS

## Responses

Markdown supported · ⌘↵ to post

No responses yet.
