Tom Lee - DEV Community

Tom Lee

Apr 6

Andrew Ng Was Right 9 Months Ago — Here's What Changed (And What Didn't)

#ai #agents #startup #opensource

1

5 min read

Tom Lee

Apr 6

AI Doesn't Need a Bigger Engine. It Needs a Seatbelt.

#ai #security #opensource #startup

1

4 min read

Tom Lee

Apr 6

The Forest Has Parasites: Why AI Agent Security Needs Runtime Defense

#ai #security #opensource #startup

1

4 min read

Tom Lee

Apr 6

The Cognitive Dark Forest Has One Exit: Become the Forest

#opensource #ai #strategy #startup

2

5 min read

Tom Lee

Apr 5

Anthropic Proved AI Has Functional Emotions — Persona Design Is Now a Safety Issue

#ai #safety #anthropic #machinelearning

2

4 min read

Tom Lee

Apr 5

Harvard Proved Emotions Don't Make AI Smarter — That's Exactly Why You Need Soul Spec

#ai #promptengineering #research #identity

1

4 min read

Tom Lee

Apr 4

From Third-Party Agent to Claude Code Native: ClawSouls Plugin Launch

#claude #ai #opensource #productivity

5 min read

Tom Lee

Apr 3

The Interface Problem Is Solved. The Identity Problem Isn't.

#ai #agents #soulspec #security

1

4 min read

Tom Lee

Apr 2

NVIDIA Shares Tensors Between GPUs. Soul Spec Shares Behavior Between Agents. Both Are Harness Engineering.

#ai #nvidia #agents #infrastructure

4 min read

Tom Lee

Apr 2

Prompt Context Harness: The Three Stages of AI Engineering and Why the Third Changes Everything

#ai #agents #engineering #opensource

4 min read

Tom Lee

Apr 2

What the Claude Code Leak Reveals: The Engine Isn't the Moat — The Harness Is

#ai #claudecode #agents #opensource

4 min read

Tom Lee

Apr 2

81,000 People Told Anthropic What They Really Want from AI — It's Not What You Think

#ai #safety #agents #anthropic

2

3 min read

Tom Lee

Apr 1

Prompt Engineering vs Context Engineering: Why the Shift Matters

#ai #agents #souls #openclaw

1

1 min read

Tom Lee

Apr 1

What Anthropic Just Proved — AI Personas Aren't Prompts, They're Identities

#ai #agents #souls #openclaw

1 min read

Tom Lee

Apr 1

Anthropic Publishes Official Skills Guide — How It Compares to Soul Spec

#ai #agents #souls #openclaw

2 min read

Tom Lee

Apr 1

The Agent Brain: Mapping AI Agent Components to Human Neural Architecture

#ai #agents #souls #openclaw

1 min read

Tom Lee

Apr 1

From Asimov to JSON: Operationalizing Robot Safety Laws in Agent Identity Files

#ai #safety #agents #asimov

2

1 min read

Tom Lee

Mar 31

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

#maatspec #llmsafety #aiagents #research

5 min read

Tom Lee

Mar 31

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

#soulclaw #soulscan #persona #swarm

1

4 min read

Tom Lee

Mar 31

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

#soulspec #persona #aisafety #research

4 min read

Tom Lee

Mar 31

The Soul-Evil Attack: How Malicious Personas Hijack AI Agents (And How to Stop Them)

#soulscan #security #aiagents #soulspec

6 min read

Tom Lee

Mar 31

The Model Isn't the Bottleneck — Your Prompt Structure Is

#contextengineering #soulspec #llm #prompting

3 min read

Tom Lee

Mar 31

Every AI Project Becomes an Agent — And Every Agent Needs a Soul

#aiagents #soulspec #guardrails #contextengineering

3 min read

Tom Lee

Mar 31

The ClawHub Malware Incident: A First Warning for AI Agent Supply Chains

#security #supplychain #clawhub #soulscan

4 min read

Tom Lee

Mar 31

Cross-Model Persona Fidelity: Is Your AI Agent Still 'Them' on a Different LLM?

#research #soulspec #persona #llm

2 min read

Tom Lee

Mar 31

Shadow AI Detection Tools Compared: Claw-Hunter vs openclaw-detect

#security #shadowai #enterprise #mdm

4 min read

Tom Lee

Mar 31

Can AI Agents Detect Their Own Model Upgrades?

#research #soulspec #aiconsciousness #introspection

3 min read

Tom Lee

Mar 31

Persona Persistence Attacks: When Your AI Agent's Soul File Becomes a Backdoor

#security #soulscan #research #soulspec

2 min read

Tom Lee

Mar 31

Soul Spec + MaatSpec: Identity and Governance as Complementary Layers for AI Agents

#aiagents #governance #soulspec #identity

4 min read

Tom Lee

Mar 31

The 'AI Wrapper' Is the Moat Now

#contextengineering #soulspec #aiux #businessmodel

3 min read

Tom Lee

Mar 31

Soul Rollback & Swarm Memory: Protecting AI Agent Identity at Scale

#soulrollback #swarmmemory #security #multiagent

3 min read

Tom Lee

Mar 31

Introducing ClawSouls Agent: AI with Personality in Your Editor

#clawsouls #vscode #agents #swarmmemory

2 min read

Tom Lee

Mar 31

Why Local LLMs Can't Hold a Persona (And Claude Can)

#persona #localllm #ollama #claude

4 min read

Tom Lee

Mar 31

Why Context Compaction Kills Your Agent's Personality (And How to Fix It)

#soulspec #persona #contextwindow #aiagents

5 min read

Tom Lee

Mar 31

How SoulClaw Cuts Token Usage by 60% With Tiered Bootstrap Loading

#soulclaw #contextwindow #tokenoptimization #openclaw

1

3 min read

Tom Lee

Mar 31

IronClaw vs OpenClaw: Rust Rewrite vs the Original — What's Better?

#ironclaw #openclaw #soulclaw #rust

5 min read

Tom Lee

Mar 31

ClawSouls Registry: The Open AI Persona Registry with Automated Safety Verification

#clawsouls #aiagents #opensource #safety

3 min read

Tom Lee

Mar 25

What is Soul-Driven AI?

#ai #agents #opensource #identity

2

4 min read

Tom Lee

Mar 25

FTS vs Hybrid Memory Search: A Real-World Benchmark

#ai #benchmark #search #agents

1

4 min read

Tom Lee

Mar 21

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

#ai #llm #safety #research

1

2

5 min read

Tom Lee

Mar 21

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

#ai #safety #llm #research

1 min read

Tom Lee

Mar 20

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

#ai #research #memory #identity

2

3 min read

Tom Lee

Mar 20

The Human in the Loop of Identity

#ai #agents #identity #philosophy

5 min read

Tom Lee

Mar 20

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

#ai #agents #memory #transformers

4 min read

Tom Lee

Mar 20

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

#ai #agents #payments #security

4 min read

Tom Lee

Mar 20

Everything Claude Code Experts Recommend, We Already Built Into SoulClaw

#ai #claudecode #devtools #programming

4 min read

Tom Lee

Mar 20

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

#ai #agents #memory #architecture

4 min read

Tom Lee

Mar 20

Perfect Memory Is Breaking Your AI Agent's Identity

#ai #agents #memory #identity

1

4 min read

Tom Lee

Mar 19

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

#ai #llm #machinelearning #research

4 min read

Tom Lee

Mar 18

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

#ai #opensource #security #agents

2 min read

Tom Lee

Mar 17

3-Tier Memory: How SoulClaw Agents Never Forget

#ai #opensource #architecture #database

1

3 min read

Tom Lee

Mar 11

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

#ai #agents #security #opensource

4 min read

Tom Lee

Mar 11

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

#ai #security #opensource #meta

1

3 min read

Tom Lee

Mar 10

Why Vibecoding Fails — AI Agents Need Memory and Identity

#ai #coding #opensource #devtools

3 min read

Tom Lee

Feb 24

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

#ai #programming #cursor #claudecode

1

11 min read

Tom Lee

Feb 24

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

#ai #openclaw #tutorial #productivity

1

10 min read

Writing Debut

Want to connect with Tom Lee?