DEV Community

Max Quimby profile picture

Max Quimby

Tech lead in computeleap.com

Washington Joined on  https://computeleap.com
Free-Model Playbook for Claude Code and Codex

Free-Model Playbook for Claude Code and Codex

1
6 min read

Want to connect with Max Quimby?

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

Already have an account? Sign in
GPT-5.6 Sol Ships Gated — the Gate Is the Story

GPT-5.6 Sol Ships Gated — the Gate Is the Story

1
5 min read
DSpark: Open-Weight Speed Without a Cerebras Contract

DSpark: Open-Weight Speed Without a Cerebras Contract

1
3 min read
What Is DESIGN.md and Why Your Agent Needs One

What Is DESIGN.md and Why Your Agent Needs One

1
9 min read
The AI Memory Squeeze Has Hit Your Wallet

The AI Memory Squeeze Has Hit Your Wallet

1
11 min read
The Weights Embargo

The Weights Embargo

2
7 min read
The Agent-of-Agents Problem: Orchestrating a Fleet

The Agent-of-Agents Problem: Orchestrating a Fleet

2
5 min read
Krea 2: Open-Weights Image Model That Caught the Frontier

Krea 2: Open-Weights Image Model That Caught the Frontier

2
3 min read
Claude Tag: How the Per-Thread Sandbox Works

Claude Tag: How the Per-Thread Sandbox Works

2
9 min read
Unlimited-OCR vs Mistral OCR 4: Which One Wins?

Unlimited-OCR vs Mistral OCR 4: Which One Wins?

2
9 min read
China Just Won the Rare-Earths Race

China Just Won the Rare-Earths Race

2
2 min read
Write HTML, Not JSON: HeyGen's Visual-Grounding Trick

Write HTML, Not JSON: HeyGen's Visual-Grounding Trick

2
3 min read
GLM-5.2 Is Cheap Because It's Subsidized, Not Efficient

GLM-5.2 Is Cheap Because It's Subsidized, Not Efficient

2
5 min read
Z.ai Open-Sourced slime: GLM-5.2 Post-Training Stack

Z.ai Open-Sourced slime: GLM-5.2 Post-Training Stack

3
10 min read
Artifacts in Claude Code: The Operator's Guide

Artifacts in Claude Code: The Operator's Guide

3
1
6 min read
GLM-5.2 vs Opus 4.8: The Open-Weights Moat Is Real

GLM-5.2 vs Opus 4.8: The Open-Weights Moat Is Real

2
10 min read
Anthropic Walked Back the Agent SDK Credit Change

Anthropic Walked Back the Agent SDK Credit Change

2
7 min read
Apple Paying Google $1B/Year to Run Siri on Gemini

Apple Paying Google $1B/Year to Run Siri on Gemini

3
10 min read
The Narration War: Who Defines the Fable 5 Freeze

The Narration War: Who Defines the Fable 5 Freeze

1
4 min read
Run Your Coding Agent on Local Weights: Operator Playbook

Run Your Coding Agent on Local Weights: Operator Playbook

2
4 min read
OpenRouter Fusion vs Claude Fable 5: 7x Slower, 4x the Cost

OpenRouter Fusion vs Claude Fable 5: 7x Slower, 4x the Cost

2
3 min read
MDASH: How 100 Agents Beat One Frontier Model

MDASH: How 100 Agents Beat One Frontier Model

1
8 min read
Run GLM-5.2 Locally: The Open Model Nobody Can Ban

Run GLM-5.2 Locally: The Open Model Nobody Can Ban

18
10 min read
The Harness Is the Moat

The Harness Is the Moat

1
4 min read
Why the US Government Pulled Fable 5

Why the US Government Pulled Fable 5

1
10 min read
The Trillionaire Playbook

The Trillionaire Playbook

2
5 min read
Loopcraft: Stop Prompting, Start Designing Loops

Loopcraft: Stop Prompting, Start Designing Loops

2
2
6 min read
Is the AI Scaling Law Breaking? The Capex Math

Is the AI Scaling Law Breaking? The Capex Math

2
8 min read
Don't Run That Skill Yet

Don't Run That Skill Yet

2
3 min read
Anthropic Reverses the Fable 5 Research Restriction

Anthropic Reverses the Fable 5 Research Restriction

2
4 min read
The Apache Exchange: US-Iran Goes Direct

The Apache Exchange: US-Iran Goes Direct

2
9 min read
Skills Are Eating GitHub Trending

Skills Are Eating GitHub Trending

2
9 min read
DiffusionGemma: Open-Weight Text at 1,000 Tokens/Sec

DiffusionGemma: Open-Weight Text at 1,000 Tokens/Sec

2
10 min read
10x PRs, 1x Reviewers: The Code-Quality Bottleneck

10x PRs, 1x Reviewers: The Code-Quality Bottleneck

2
11 min read
Claude Fable 5 Is Mythos 5 — With a Muzzle

Claude Fable 5 Is Mythos 5 — With a Muzzle

2
5 min read
The Ceasefire That Wasn't: How the Iran-Israel War Just Unwound the AI Trade

The Ceasefire That Wasn't: How the Iran-Israel War Just Unwound the AI Trade

4 min read
Config Files That Run Code: The Agent Skill Supply Chain

Config Files That Run Code: The Agent Skill Supply Chain

10 min read
Local LLMs Answer 71% of Real Queries: MiMo Sets the Bar

Local LLMs Answer 71% of Real Queries: MiMo Sets the Bar

10 min read
Nationalize AI? Bernie's 50% Stake vs. Trump's Partnership

Nationalize AI? Bernie's 50% Stake vs. Trump's Partnership

6 min read
Run Anthropic's Vuln-Discovery Harness on Your Code

Run Anthropic's Vuln-Discovery Harness on Your Code

9 min read
AI's $700B Subsidy Clock Is Ticking

AI's $700B Subsidy Clock Is Ticking

6 min read
Gemma 4 12B: Encoder-Free Coding on a 16GB Laptop

Gemma 4 12B: Encoder-Free Coding on a 16GB Laptop

1
10 min read
China's Coding AI Is Closing the Gap Fast

China's Coding AI Is Closing the Gap Fast

1
4 min read
Anthropic's S-1: What a $965B IPO Filing Changes

Anthropic's S-1: What a $965B IPO Filing Changes

1
5 min read
Russia's Oreshnik on Kyiv: The Strike Nobody Could Stop

Russia's Oreshnik on Kyiv: The Strike Nobody Could Stop

6 min read
Pope Leo's AI Encyclical: An Enterprise Governance Decoder

Pope Leo's AI Encyclical: An Enterprise Governance Decoder

7 min read
Claude for Small Business: 382K Day-One Buyer's Guide

Claude for Small Business: 382K Day-One Buyer's Guide

9 min read
codegraph: The Missing Knowledge Graph for 5 Coding Agents

codegraph: The Missing Knowledge Graph for 5 Coding Agents

1
3 min read
What Microsoft Canceling Claude Code Means for Enterprise AI

What Microsoft Canceling Claude Code Means for Enterprise AI

1
5 min read
Antigravity 2.0 Review: The Switching-Cost Trap

Antigravity 2.0 Review: The Switching-Cost Trap

7 min read
Gemini 3.5 Flash: Is 'Cheaper Than Frontier' Real?

Gemini 3.5 Flash: Is 'Cheaper Than Frontier' Real?

9 min read
Chamath's 18 Months: Taiwan, TSMC-Arizona, and the Clock

Chamath's 18 Months: Taiwan, TSMC-Arizona, and the Clock

1
10 min read
Long-Running Agents: Harness, Evaluator, Handoff

Long-Running Agents: Harness, Evaluator, Handoff

1
10 min read
Anthropic at 92%: Three Surfaces Tell the Same Story

Anthropic at 92%: Three Surfaces Tell the Same Story

1
10 min read
Codex Pulling Ahead of Claude Code? Read the 2026 Shift

Codex Pulling Ahead of Claude Code? Read the 2026 Shift

2
9 min read
Per-Seat SaaS Is a Liability: A 2026 Operator's Checklist

Per-Seat SaaS Is a Liability: A 2026 Operator's Checklist

10 min read
AI Psychosis in Your Agent Stack: A 9-Point Audit

AI Psychosis in Your Agent Stack: A 9-Point Audit

10 min read
Inference Inflection: Cerebras, SpaceX, Leopold's $5.5B Bet

Inference Inflection: Cerebras, SpaceX, Leopold's $5.5B Bet

12 min read
Xi Said the Quiet Part: Taiwan 'Could Trigger Conflict'

Xi Said the Quiet Part: Taiwan 'Could Trigger Conflict'

7 min read
Three Humanoid Robots Just Quietly Cracked Their Records

Three Humanoid Robots Just Quietly Cracked Their Records

7 min read
loading...