1.04M subscribers
Official YouTube channel
Cursor & IDE agents · Comparisons & reviews · Evals & benchmarks
All videos
Video topic · 72 videos
Comparisons & reviews
Head-to-head comparisons and reviews of harnesses, tools and models.
Who covers it
Everyone on this topic4.32M subscribers
Creator on YouTube
Security & sandboxes · Comparisons & reviews
Channel · 371K subscribers
Podcast on YouTube
Talks & interviews · Codex & OpenAI agents · Comparisons & reviews
1.01M subscribers
Creator on YouTube
Claude Code · Comparisons & reviews · Open harnesses
114K subscribers
Creator on YouTube
OpenClaw, Hermes & personal agents · Skills, plugins & mods · Comparisons & reviews
252K subscribers
Creator on YouTube
Context engineering & memory · Comparisons & reviews · Evals & benchmarks
Videos, newest first
Visual Studio Code · Oct 28, 2026
🍰 Compare Models & Harnesses with Agent Bake Off!
Comparisons & reviews · Evals & benchmarks
How I AI · Oct 28, 2026
I tested 4 AI agents on 9 real tasks. Here’s who won.
OpenClaw, Hermes & personal agents · Comparisons & reviews
David Ondrej · Oct 28, 2026
kimi k3.1 changes everything...
Comparisons & reviews
Zero to MVP (Nick Blokhin) · Oct 27, 2026
$7 vs $0.65: Opus 5.5 and MiniMax M3.1 Flash on My Go Project
Comparisons & reviews · Cost & limits
Prompt Engineering · Oct 25, 2026
Kimi K3.1 Pro and Opus 5.5 Made the Same 13 Apps (Raw Results)
Comparisons & reviews · Evals & benchmarks
Income stream surfers · Oct 25, 2026
RIP Claude Code: Kimi K3.1 + Kimi Code = INSANE CHEAP CODING SETUP
Comparisons & reviews · Cost & limits
Erwan | IA · Oct 24, 2026 · French
Kimi K3.1 Pro a-t-il rattrapé Opus 5.5 et GPT 6 Astra ?
Comparisons & reviews
WorldofAI · Oct 24, 2026
Kimi K3.1 Pro Is INSANE! CHEAPER & FASTER Than Claude Opus 5.5?! (Fully Tested)
Comparisons & reviews · Evals & benchmarks
Zero to MVP (Nick Blokhin) · Oct 24, 2026
Kimi K3.1 Pro Is Nearly Opus 5.5 on Paper. What About a Real Project?
Comparisons & reviews
Juan Pe Navarro · Oct 23, 2026 · Spanish
Hermes Agent vs OpenClaw: Los Enfrenté en 6 Asaltos y Ganó el Mejor
OpenClaw, Hermes & personal agents · Comparisons & reviews
Prompt Engineering · Oct 23, 2026
Kimi K3.1 Pro: Open Weights, Almost Opus
Comparisons & reviews
AICodeKing · Oct 22, 2026
Recursive Flint: This OPEN Local Coding Model is CRAZY! (Tested with Pi, OpenCode & PandaCode)
Open harnesses · Comparisons & reviews
Peter Yang · Oct 21, 2026
Claude Duet Is Here! (Better than Grok Bot?)
OpenClaw, Hermes & personal agents · Comparisons & reviews
Ras Mic · Oct 21, 2026
I stopped using Claude Code...
Claude Code · Comparisons & reviews
How I AI · Oct 21, 2026
I tested Claude Duet. Is it worth switching from Grok Bot?
OpenClaw, Hermes & personal agents · Comparisons & reviews
Fireship · Oct 20, 2026
Did Google just dethrone OpenAI and Anthropic?
Comparisons & reviews
The Gray Cat · Oct 20, 2026
I Tested 4 Codex Frameworks on the Same Real Feature
Codex & OpenAI agents · Comparisons & reviews
잔재미코딩 (Dave Lee) · Oct 20, 2026 · Short · Korean
딥시크 v4.1, 클로드 오퍼스 5의 약 60분의 1 비용으로 코딩 #Shorts #딥시크 #DeepSeek #클로드코드
Cost & limits · Comparisons & reviews
Nate Herk | AI Automation · Oct 19, 2026
I Tried 100+ AI Tools. These 7 Are the Best
Comparisons & reviews
AICodeKing · Oct 19, 2026
Opus + Sol Orchestrated Team: This BEATS every AI MODEL right now! (Tested)
Multi-agent orchestration · Comparisons & reviews
Zero to MVP (Nick Blokhin) · Oct 18, 2026
New DeepSeek V4.1 Flash vs Claude Opus 5.5 on a 20,000-Line Project
Comparisons & reviews
Latent Space · Oct 16, 2026
High Taste Testers: OpenAI Shipped Everything. What Actually Works?
Codex & OpenAI agents · Comparisons & reviews
Zero to MVP (Nick Blokhin) · Oct 13, 2026
Claude Haiku 5.5 vs Local Qwen 3.8 27B: Is Local AI Still Worth It?
Comparisons & reviews
The Gray Cat · Oct 13, 2026
Understand Anything vs Groma: Two Ways to Learn Your Code
Context engineering & memory · Comparisons & reviews
WorldofAI · Oct 12, 2026
Meta's Muse Wonder IS OPUS 5.5 LEVEL?! I Don't Think So... (Fully Tested)
Comparisons & reviews
김플립 - LLM 코딩 (Kimflip) · Oct 6, 2026 · Korean
머스크가 인정한 AI 티어표, 요즘 AI모델 버전업 근황 (오퍼스 5.5 · 소넷 5.5 · GPT-6.1 솔) 총정리
Comparisons & reviews
The Gray Cat · Oct 6, 2026
I Tested 6 Code Graph Tools—Here Is What Actually Happened
Context engineering & memory · MCP & tools · Comparisons & reviews
IndyDevDan · Oct 5, 2026
OpenRouter State Of Models: Jev, Open-Weights, and Tokenomics
Cost & limits · Comparisons & reviews
David Ondrej · Oct 2, 2026
Opus 5.5 almost lost to an open-source model...
Comparisons & reviews · Open harnesses
Meydeey (Le Labo IA) · Sep 29, 2026 · French
Pourquoi payer encore Opus 5.5 ? (Sonnet 5.5)
Cost & limits · Comparisons & reviews
The Gray Cat · Sep 29, 2026
Purr Request: unlazy — More Tokens, Worse Code?
Skills, plugins & mods · Comparisons & reviews
Fabio Basler (AI Fabio) · Sep 28, 2026 · German
Opus 5.5 vs. GPT 6: wer baut bessere Websites?
Comparisons & reviews
김플립 - LLM 코딩 (Kimflip) · Sep 26, 2026 · Korean
코딩 모델, 그냥 Opus 5.5 쓰세요! 3일 써보고 내린 결론 #ai코딩 #claudecode #claude #astra #chatgpt
Comparisons & reviews
Zero to MVP (Nick Blokhin) · Sep 25, 2026
GPT-6 Sol vs Opus 5.5 — Picking My New Daily Driver
Comparisons & reviews
Benjamín Cordero · Sep 16, 2026 · Spanish
¿Me cambio a Codex o sigo con Claude Code?
Comparisons & reviews
김플립 - LLM 코딩 (Kimflip) · Sep 9, 2026 · Korean
GPT-6 Astra 소름 돋게 잘하다가 왜 이래? 개발자적 측면에서 솔직 후기 #gpt6 #astra #claude #ai코딩 #바이브코딩
Codex & OpenAI agents · Comparisons & reviews
The Gray Cat · Sep 8, 2026
I Tested Superpowers v6 vs Grill Me: The Results Are Shocking
Skills, plugins & mods · Comparisons & reviews
김플립 - LLM 코딩 (Kimflip) · Sep 2, 2026 · Korean
Claude Fable 5.1 나왔습니다 — 1분만에 총정리 (성능·가격·구독 제한) #claudecode #Claude #Fable51#AI #LLM
Comparisons & reviews · Cost & limits
The Gray Cat · Sep 1, 2026
Caveman vs Ponytail vs RTK: Which Saves Most Tokens?
Cost & limits · Comparisons & reviews
Anthropic · Sep 1, 2026
Introducing Claude Fable 5.1
Comparisons & reviews
The Gray Cat · Aug 27, 2026
Matt Pocock vs Addy Osmani: I Tested Both Skill Packs
Skills, plugins & mods · Comparisons & reviews
Owain Lewis · Aug 22, 2026
I Tested DeepSeek Agent Harness Against Codex and Claude Code
Open harnesses · Comparisons & reviews
Ras Mic · Aug 14, 2026
I'm done with Claude Code
Claude Code · Comparisons & reviews
The Gray Cat · Aug 13, 2026
Beads vs Backlog.md vs Claude Code Native Tasks
Claude Code · Comparisons & reviews
AI Growth TV Hub · Aug 9, 2026
I Tested Old No-Code Tools Against AI Vibe Coding — Here's What Survived
Cost & limits · Comparisons & reviews
Anthony Marandon · Aug 4, 2026 · French
l'IA GRATUITE suffit-elle pour coder ? (le test honnête)
Cost & limits · Comparisons & reviews
Anthony Marandon · Jul 31, 2026 · French
J'ai comparé les 3 agents IA les plus puissants : voici le gagnant
Comparisons & reviews
김플립 - LLM 코딩 (Kimflip) · Jul 25, 2026 · Korean
페이블 절반 가격에 페이블급?! Claude Opus 5 왕의 귀환
Comparisons & reviews
Ras Mic · Jul 24, 2026
Which Al Subscription is worth the cost? (Codex vs Claude Code vs Cursor)
Comparisons & reviews · Cost & limits
IndyDevDan · Jul 20, 2026
Engineers... STOP Picking GPT-5.6 Sol OR Claude Fable 5… FUSE THEM
Multi-agent orchestration · Comparisons & reviews
Kilo · Jul 20, 2026
GPT 5.6 vs. Fable 5 - Who's better at planning?
Comparisons & reviews
Owain Lewis · Jul 17, 2026
I Replaced Hermes Agent And OpenClaw With This
OpenClaw, Hermes & personal agents · Comparisons & reviews
Amit Explains Tech · Jul 16, 2026 · Hindi
Qoder AI Coding Agent vs Cursor — Honest Comparison
Cursor & IDE agents · Comparisons & reviews
OpenHands · Jul 9, 2026
The Best AI Coding Models Right Now (OpenHands Index Update)
Evals & benchmarks · Comparisons & reviews
Tarek Alabd · Jul 4, 2026 · Arabic
أنا جربت OpenCode واتصدمت! تعالى أقولك الخلاصة
Open harnesses · Comparisons & reviews
Theo - t3.gg · May 26, 2026
Claude Code vs Codex vs Cursor (an honest comparison)
Comparisons & reviews · Claude Code · Codex & OpenAI agents
Vibe Coding Studio【AI駆動開発実践】 · Mar 24, 2026 · Japanese
Verdent AIを初見レビュー！Planモード・並列・マルチモデルレビューを試した感想
Cursor & IDE agents · Comparisons & reviews
IndyDevDan · Feb 23, 2026
The Pi Coding Agent: The ONLY REAL Claude Code COMPETITOR
Open harnesses · Comparisons & reviews
Roo Code · Feb 20, 2026
Gemini 3.1 Review || Roo Code Router
Open harnesses · Comparisons & reviews
Roo Code · Feb 18, 2026
Claude Sonnet 4.6 in Roo Code || Official Test and Review
Open harnesses · Comparisons & reviews
Theo - t3.gg · Feb 17, 2026
A realistic comparison of Opus and Codex
Comparisons & reviews · Codex & OpenAI agents
Roo Code · Feb 6, 2026
The New Frontier: Claude Opus 4.6 and GPT Codex 5.3 in Roo Code
Open harnesses · Comparisons & reviews
Anthropic · Feb 5, 2026
Introducing Claude Opus 4.6
Comparisons & reviews
Rasmus Widing · Jan 12, 2026
Parallel AI Agents vs Single Agents: What Actually Works
Multi-agent orchestration · Comparisons & reviews
Rasmus Widing · Jan 5, 2026
Is This AI Coding Tool Worth Switching To? vs Claude Code
Comparisons & reviews
GosuCoder · Dec 24, 2025
Coding with GLM 4.7 and 2025 reflections | Story time
Comparisons & reviews
GosuCoder · Dec 1, 2025
Top AI Coding Agents Dec 2025 | Opus 4.5, Gemini 3.0 Pro, GPT 5.1
Comparisons & reviews · Evals & benchmarks
GosuCoder · Nov 26, 2025
AI Coding has changed so much with Gemini 3 Pro and Opus 4.5
Comparisons & reviews
Brian Casel · Nov 12, 2025
Claude Code vs. Cursor vs. Codex: Cloud Agents Showdown
Comparisons & reviews · Multi-agent orchestration
GosuCoder · Oct 1, 2025
Best AI coding Agents with some interesting results | Sonnet 4.5, GLM 4.6, Grok Code, GPT 5 Codex
Comparisons & reviews · Evals & benchmarks
GosuCoder · Sep 1, 2025
Best AI coding Agents with some crazy upsets | GPT 5, Grok Code Fast, Claude, Qwen 3 Coder
Comparisons & reviews · Evals & benchmarks
Rasmus Widing · Jul 11, 2025
Claude Code vs Gemini CLI: Live PRP Battle - Gemini at 39% context after ONE prompt!
Comparisons & reviews · Claude Code
Claude CodeCodex & OpenAI agentsOpen harnessesOpenClaw, Hermes & personal agentsCursor & IDE agentsMCP & toolsSkills, plugins & modsMulti-agent orchestrationContext engineering & memoryEvals & benchmarksSecurity & sandboxesCost & limitsHarness engineeringTutorials & getting startedTalks & interviews