Olivier olinguyen

Final Review - Comprehensive PR Review & Testing

Step 0: Determine Review Pass

Before starting, check the git history to determine if this is a follow-up review:

git log --oneline -10 | grep -i "Co-Authored-By: Claude"

name: Hook Development description: >- This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "implement agent hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", "frontmatter hooks", "scoped hooks", "once: true", or mentions hook events (PreToolUse, PostToolUse, Stop,

Knowledge Vault

A second brain that actually thinks.

What This Is

This is a personal knowledge management system that combines Obsidian (for notes) with Claude Code (for intelligence). Instead of just storing information, it actively processes, connects, and surfaces knowledge when you need it.

What it replaces:

Evernote — But AI organizes your notes for you

<core_identity> You are an assistant called Cluely, developed and created by Cluely, whose sole purpose is to analyze and solve problems asked by the user or shown on the screen. Your responses must be specific, accurate, and actionable. </core_identity>

<general_guidelines>

NEVER use meta-phrases (e.g., "let me help you", "I can see that").
NEVER summarize unless explicitly requested.
NEVER provide unsolicited advice.
NEVER refer to "screenshot" or "image" - refer to it as "the screen" if needed.
ALWAYS be specific, detailed, and accurate.

Cursor's Memory Bank

I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.

Memory Bank Structure

The Memory Bank consists of required core files and optional context files, all in Markdown format. Files build upon each other in a clear hierarchy:

flowchart TD

Reinforcement Learning for Language Models

Yoav Goldberg, April 2023.

Why RL?

With the release of the ChatGPT model and followup large language models (LLMs), there was a lot of discussion of the importance of "RLHF training", that is, "reinforcement learning from human feedback". I was puzzled for a while as to why RL (Reinforcement Learning) is better than learning from demonstrations (a.k.a supervised learning) for training language models. Shouldn't learning from demonstrations (or, in language model terminology "instruction fine tuning", learning to immitate human written answers) be sufficient? I came up with a theoretical argument that was somewhat convincing. But I came to realize there is an additional argumment which not only supports the case of RL training, but also requires it, in particular for models like ChatGPT. This additional argument is spelled out in (the first half of) a talk by John Schulman from OpenAI. This post pretty much

Chat GPT "DAN" (and other "Jailbreaks")

	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	"""
	citation:

	@misc{brown2025grpodemo,
	title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
	author={Brown, William},

	import os

	from keras import backend as K
	from keras import callbacks
	from keras import layers
	from keras import models
	from keras.wrappers.scikit_learn import KerasClassifier
	import pandas as pd
	import tensorflow as tf
	from sklearn import metrics