DEV Community

Self-Correcting Systems profile picture

Self-Correcting Systems

I run a small multi-agent system and write about the part nobody tells you: memory that keeps your corrections, not your flattery. Truth over comfort.

Joined Joined on  github website

Education

Self-taught. No degree. Learned by building, failing, and correcting.

Pronouns

He

Retrieval Is Solved. Why Agent Memory Still Isn't Safe.
zep1997 profile

Retrieval Is Solved. Why Agent Memory Still Isn't Safe.

#ai #agents #security #machinelearning
1
Comments
6 min read

Want to connect with Self-Correcting Systems?

Create an account to connect with Self-Correcting Systems. You can also sign in below to proceed if you already have an account.

Create Account
Already have an account? Sign in
The Query Was Still a Lie. The Tool Call Told the Truth.
zep1997 profile

The Query Was Still a Lie. The Tool Call Told the Truth.

#ai #security #agents #machinelearning
5
Comments 8
6 min read
Retrieval Found the Sensitive Memory. That Made It More Dangerous.
zep1997 profile

Retrieval Found the Sensitive Memory. That Made It More Dangerous.

#ai #machinelearning #agentmemory #security
1
Comments 2
8 min read
I Tried to Turn Agent Memory Authority Into a Scoring Formula. The Held-Out Test Changed the Claim.
zep1997 profile

I Tried to Turn Agent Memory Authority Into a Scoring Formula. The Held-Out Test Changed the Claim.

#ai #machinelearning #agentmemory #security
1
Comments 1
11 min read
The Gate Was Reading the Memory's Own Lie. Here's What I Built Instead.
zep1997 profile

The Gate Was Reading the Memory's Own Lie. Here's What I Built Instead.

#ai #agents #architecture #security
2
Comments 14
3 min read
Retrieval Found the Memory. But What Authorized the Action?
zep1997 profile

Retrieval Found the Memory. But What Authorized the Action?

#ai #machinelearning #programming #security
3
Comments 6
5 min read
Agent Memory Card Generator — One Prompt Turned Into a Governance Dashboard

Education Track: Build Apps with Google AI Studio
zep1997 profile

Agent Memory Card Generator — One Prompt Turned Into a Governance Dashboard

#deved #learngoogleaistudio #ai #gemini
1
Comments
3 min read
I Found a Design Bound for Agent Memory Safety. Now I Need External Pressure.
zep1997 profile

I Found a Design Bound for Agent Memory Safety. Now I Need External Pressure.

#discuss #ai #machinelearning #programming
1
Comments 12
5 min read
I Built a Multi-Agent Authority Auditor for AI Memory Files

Education Track: Build Multi-Agent Systems with ADK
zep1997 profile

I Built a Multi-Agent Authority Auditor for AI Memory Files

#agents #buildmultiagents #gemini #adk
2
Comments 2
4 min read
Start Here: My AI Memory Research So Far
zep1997 profile

Start Here: My AI Memory Research So Far

#discuss #ai #agents #machinelearning
1
Comments
5 min read
Testing an AI Memory Reliability Checklist on 3 Redacted Agent Setups
zep1997 profile

Testing an AI Memory Reliability Checklist on 3 Redacted Agent Setups

#ai #agents #productivity #machinelearning
1
Comments
2 min read
Before I Would Trust an Agent's Memory, I Would Audit Its Authority

Hermes Agent Challenge Submission: Write About Hermes Agent
zep1997 profile

Before I Would Trust an Agent's Memory, I Would Audit Its Authority

#hermesagentchallenge #ai #devchallenge #agents
6
Comments 25
7 min read
I Published an AI Memory Result. Then Real Retrieval Broke Everything.
zep1997 profile

I Published an AI Memory Result. Then Real Retrieval Broke Everything.

#ai #machinelearning #githubchallenge #devchallenge
1
Comments
5 min read
In This Memory Test, Relevance Wasn't Authority
zep1997 profile

In This Memory Test, Relevance Wasn't Authority

#ai #machinelearning #rag #agents
1
Comments 6
9 min read
Higher Retrieval Accuracy Had the Worse Safety Result
zep1997 profile

Higher Retrieval Accuracy Had the Worse Safety Result

#ai #machinelearning #llm #rag
1
Comments 2
5 min read
I Tested Three AI Memory Retrieval Strategies. The Hard Failure Was Semantic
zep1997 profile

I Tested Three AI Memory Retrieval Strategies. The Hard Failure Was Semantic

#ai #llm #machinelearning #agents
Comments
8 min read
AI Memory Is Not Storage. It Is Judgment Infrastructure.
zep1997 profile

AI Memory Is Not Storage. It Is Judgment Infrastructure.

#ai #agents #machinelearning #architecture
Comments
4 min read
AI Memory Should Decide What Context Is Allowed To Do
zep1997 profile

AI Memory Should Decide What Context Is Allowed To Do

#ai #llm #agents #programming
Comments
5 min read
AI Memory Needs an Authority Policy, Not Just More Context
zep1997 profile

AI Memory Needs an Authority Policy, Not Just More Context

#ai #llm #agents #programming
Comments 2
7 min read
Three Failures My AI Memory System Tested — And the Flaw It Revealed in Itself
zep1997 profile

Three Failures My AI Memory System Tested — And the Flaw It Revealed in Itself

#ai #machinelearning #llm #programming
Comments
6 min read
The Zero-Budget AI Memory System That Survives Session Resets No database. No framework. Just files, startup order, correction logs, and discipline.
zep1997 profile

The Zero-Budget AI Memory System That Survives Session Resets No database. No framework. Just files, startup order, correction logs, and discipline.

#ai #automation #agents #productivity
Comments
9 min read
Why AI Memory Systems Fail at Uncertainty Preserve unresolved questions instead of forcing premature closure
zep1997 profile

Why AI Memory Systems Fail at Uncertainty Preserve unresolved questions instead of forcing premature closure

#ai #agents #productivity #automation
1
Comments 10
11 min read
Why Much AI Memory Risks Rotting — The Exception Is the Memory of Being Wrong
zep1997 profile

Why Much AI Memory Risks Rotting — The Exception Is the Memory of Being Wrong

#ai #llm #agents #productivity
Comments
11 min read
loading...