DEV Community

Tom Lee profile picture

Tom Lee

​I am a developer who aims to contribute to the greater good.

Location Seoul, Republic of Korea Joined Joined on  github website
Identity + Governance = 100% Safety? Testing Combined Persona Approaches on Abliterated LLMs
tomleelive profile

Identity + Governance = 100% Safety? Testing Combined Persona Approaches on Abliterated LLMs

#ai #llm #safety #research
1
Comments
5 min read

Want to connect with Tom Lee?

Create an account to connect with Tom Lee. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
Can AI Personas Actually Make Unsafe Models Safer? Our Experiment Says: It Depends
tomleelive profile

Can AI Personas Actually Make Unsafe Models Safer? Our Experiment Says: It Depends

#ai #safety #llm #research
Comments
1 min read
Paper: The Forgetting Problem — Why Perfect Memory Breaks AI Agent Identity
tomleelive profile

Paper: The Forgetting Problem — Why Perfect Memory Breaks AI Agent Identity

#ai #research #memory #identity
2
Comments 1
3 min read
The Human in the Loop of Identity
tomleelive profile

The Human in the Loop of Identity

#ai #agents #identity #philosophy
Comments
5 min read
Why a Perfect-Memory AI Agent Without Persona Drift is Architecturally Impossible
tomleelive profile

Why a Perfect-Memory AI Agent Without Persona Drift is Architecturally Impossible

#ai #agents #memory #transformers
Comments
4 min read
When AI Agents Have Wallets: Why Identity Becomes a Security Problem
tomleelive profile

When AI Agents Have Wallets: Why Identity Becomes a Security Problem

#ai #agents #payments #security
Comments
4 min read
Everything Claude Code Experts Recommend, We Already Built Into SoulClaw
tomleelive profile

Everything Claude Code Experts Recommend, We Already Built Into SoulClaw

#ai #claudecode #devtools #programming
Comments
4 min read
Soul Memory: A 4-Tier Adaptive Memory Architecture for AI Agents
tomleelive profile

Soul Memory: A 4-Tier Adaptive Memory Architecture for AI Agents

#ai #agents #memory #architecture
Comments
4 min read
Perfect Memory Is Breaking Your AI Agent's Identity
tomleelive profile

Perfect Memory Is Breaking Your AI Agent's Identity

#ai #agents #memory #identity
1
Comments
4 min read
NeurIPS 2025 Proved It: Every LLM Says the Same Thing — Here's the Fix
tomleelive profile

NeurIPS 2025 Proved It: Every LLM Says the Same Thing — Here's the Fix

#ai #llm #machinelearning #research
Comments
4 min read
Building Safe Agents with Long-Term Memory: SoulScan, Persona Engine & Swarm Memory
tomleelive profile

Building Safe Agents with Long-Term Memory: SoulScan, Persona Engine & Swarm Memory

#ai #opensource #security #agents
Comments
2 min read
3-Tier Memory: How SoulClaw Agents Never Forget
tomleelive profile

3-Tier Memory: How SoulClaw Agents Never Forget

#ai #opensource #architecture #database
1
Comments
3 min read
Files Are the New API — But Who's Checking the Files?
tomleelive profile

Files Are the New API — But Who's Checking the Files?

#ai #agents #security #opensource
Comments
4 min read
What If Moltbook Had SoulScan? Lessons from the AI Agent Social Network Security Breach
tomleelive profile

What If Moltbook Had SoulScan? Lessons from the AI Agent Social Network Security Breach

#ai #security #opensource #meta
1
Comments
3 min read
Why Vibecoding Fails — AI Agents Need Memory and Identity
tomleelive profile

Why Vibecoding Fails — AI Agents Need Memory and Identity

#ai #coding #opensource #devtools
Comments
3 min read
Soul Spec vs .cursorrules vs CLAUDE.md — Which AI Config Format Should You Use?
tomleelive profile

Soul Spec vs .cursorrules vs CLAUDE.md — Which AI Config Format Should You Use?

#ai #programming #cursor #claudecode
1
Comments
11 min read
The Complete SOUL.md Template Guide — Give Your AI Agent a Personality
tomleelive profile

The Complete SOUL.md Template Guide — Give Your AI Agent a Personality

#ai #openclaw #tutorial #productivity
Comments 1
10 min read
loading...