Dakota Huang

Dakota Huang

Aug 16

Model-Generated Setup Scripts: Lint the Egress Before You Run Them

#security #ai #devops #tutorial

5 min read

Dakota Huang

Aug 16

Exit Code Zero Is Not a Clean Audit: Diff the Process Tree Before You Trust a Free Model's Shell

#ai #security #linux #bash

3 min read

Dakota Huang

Aug 15

A Default-Deny Shell Is Not a Default-Deny Network: Probe What a Free Model Server Can Reach

#security #ai #devops #python

3 min read

Dakota Huang

Aug 15

A Receipt Checkpoint for Free Model Outputs Before They Become Shell Commands

#security #python #ai #devops

4 min read

Dakota Huang

Aug 15

Exit Code Zero Hides New Processes: Diff the Process Table After a Model-Generated Command

#security #linux #ai #tutorial

4 min read

Dakota Huang

Aug 15

Before You Automate a Free Model Endpoint, Measure Rate, Shape, Drift, and Budget

#ai #security #automation #python

4 min read

Dakota Huang

Aug 15

Free Server, Untrusted Model: Diff the Filesystem Before You Trust the Exit Code

#ai #devops #codequality #testing

3 min read

Dakota Huang

Aug 15

Free Servers Should Never See Your Real Credentials

#ai #security #testing #devops

4 min read

Dakota Huang

Aug 15

A Permission Matrix Before Your Free Model Touches the Shell

#ai #security #python #agents

4 min read

Dakota Huang

Aug 14

A Contract Probe for Free Model Endpoints That Drift

#ai #testing #api #devops

4 min read

Dakota Huang

Aug 14

A Streaming Response Is Not a Payload: Buffer JSON Before You Validate

#ai #json #backend #programming

1

4 min read

Dakota Huang

Aug 14

A Read-Only Gate for Model-Generated SQL on Free Compute

#ai #sql #testing #devops

4 min read

Dakota Huang

Aug 14

Draft PR Descriptions From Diffs Without Giving the Model Write Access

#ai #git #productivity #automation

3 min read

Dakota Huang

Aug 14

Split Low-Stakes Prompts From Code Changes Before You Call a Free Model

#ai #python #automation #productivity

3 min read

Dakota Huang

Aug 14

Pin Free Inference Before You Trust It: A Golden Hash Gate

#ai #testing #devops #python

4 min read

Dakota Huang

Aug 14

A Free Model Endpoint Needs a Cold-Start Budget

#ai #devops #programming #tutorial

2 min read

Dakota Huang

Aug 14

Gate the Patch, Not the Model: A Three-Check Loop for Untrusted Code Outputs

#python #ai #testing #codereview

1

5 min read

Dakota Huang

Aug 14

A Noise Budget for Free Model Evals: Live vs. Replay

#ai #python #testing #performance

5 min read

Dakota Huang

Aug 13

A Deploy Smoke Test for Model-Generated Code

#ai #programming #webdev #testing

4 min read

Dakota Huang

Aug 13

Don't Merge AI Patches Blind: A Git Worktree Replay Gate

#ai #testing #git #programming

5 min read

Dakota Huang

Aug 13

Same Model, Different Server: Fingerprint Your Eval Environment Before You Trust the Result

#python #ai #testing #devops

4 min read

Dakota Huang

Aug 13

Probe the Endpoint Before You Probe the Model

#ai #python #testing #devops

5 min read

Dakota Huang

Aug 13

A Failure Triage Script for Free Coding Models: Prompt, Model, or Wrapper?

#ai #testing #programming #python

4 min read

Dakota Huang

Aug 13

From Six Questions to a Script: My 30-Minute Eval Harness for Every New Model Release

#ai #testing #productivity #tutorial

6 min read

Dakota Huang

Aug 13

I Stopped Trusting Demo Prompts: A Repeatable Smoke Test for Free Coding Models

#ai #testing #productivity #tutorial

5 min read

Dakota Huang

Aug 12

Vibes Are Not a Benchmark: A 30-Minute Harness to Test Whether a Free Coding Model Can Touch Your Repo

#ai #productivity #python #tooling

2

5 min read

Dakota Huang

Aug 12

Stop Vibe-Checking Models: A Repeatable Comparison Harness You Can Run on Free Compute

#ai #testing #productivity #tooling

1

6 min read

Dakota Huang

Aug 10

Every New Model Gets the Same Six Questions From Me

#ai #testing #python #productivity

5 min read

DEV Community

Badges

Writing Debut

Skills/Languages

Currently learning

Currently hacking on

Available for

Model-Generated Setup Scripts: Lint the Egress Before You Run Them

Exit Code Zero Is Not a Clean Audit: Diff the Process Tree Before You Trust a Free Model's Shell

A Default-Deny Shell Is Not a Default-Deny Network: Probe What a Free Model Server Can Reach

A Receipt Checkpoint for Free Model Outputs Before They Become Shell Commands

Exit Code Zero Hides New Processes: Diff the Process Table After a Model-Generated Command

Before You Automate a Free Model Endpoint, Measure Rate, Shape, Drift, and Budget

Free Server, Untrusted Model: Diff the Filesystem Before You Trust the Exit Code

Free Servers Should Never See Your Real Credentials

A Permission Matrix Before Your Free Model Touches the Shell

A Contract Probe for Free Model Endpoints That Drift

A Streaming Response Is Not a Payload: Buffer JSON Before You Validate

A Read-Only Gate for Model-Generated SQL on Free Compute

Draft PR Descriptions From Diffs Without Giving the Model Write Access

Split Low-Stakes Prompts From Code Changes Before You Call a Free Model

Pin Free Inference Before You Trust It: A Golden Hash Gate

A Free Model Endpoint Needs a Cold-Start Budget

Gate the Patch, Not the Model: A Three-Check Loop for Untrusted Code Outputs

A Noise Budget for Free Model Evals: Live vs. Replay

A Deploy Smoke Test for Model-Generated Code

Don't Merge AI Patches Blind: A Git Worktree Replay Gate

Same Model, Different Server: Fingerprint Your Eval Environment Before You Trust the Result

Probe the Endpoint Before You Probe the Model

A Failure Triage Script for Free Coding Models: Prompt, Model, or Wrapper?

From Six Questions to a Script: My 30-Minute Eval Harness for Every New Model Release

I Stopped Trusting Demo Prompts: A Repeatable Smoke Test for Free Coding Models

Vibes Are Not a Benchmark: A 30-Minute Harness to Test Whether a Free Coding Model Can Touch Your Repo

Stop Vibe-Checking Models: A Repeatable Comparison Harness You Can Run on Free Compute

Every New Model Gets the Same Six Questions From Me