Opus 4.6
45 videos across 18 channels
Opus 4.6 sits at the center of a crowded AI-coding landscape, where debates rage over context windows, reliability, and pricing. The chatter stretches from hands-on tests and head-to-head comparisons with Claude, GLM, and Opus rivals to practical workflows that stress disciplined AI usage, cost efficiency, and hosting ecosystems. Viewers come away with a sense of ongoing nerfs, incidents, and real-world steps to navigate deployments, sponsor deals, and future improvements.
Opus 4.7 and OpenAI 5.5 Made Your Prompting Style Obsolete.
The speaker argues that prompt engineering is no longer enough and should be replaced by a higher-level “AI question met
Memory and dreaming for self learning agents
The video introduces memory and dreaming as building blocks for agents, explaining how memory lets agents learn across t
I've Changed My Opinion On Vibe Coding
The speaker revisits vibe coding, expanding beyond skepticism to describe a balanced view where AI assists learning and
Everything is pwn’d now
The video surveys a surge of security breaches across software ecosystems, explains why traditional disclosure and open
This Is Insane... The Google Stitch VS Claude Design Debate Is Finally Over
The video pits Claude Design, Google Stitch, and Gemini-powered design tools against each other across design creation,
MoonShot AI COOKED: Kimi 2.6 + Kimi Code ARE NUTS
The video analyzes Kimmy and competing AI models, starts with how the host believes Kimmy is best used via Kimmy Code CL
Rubber Duck Thursdays!
The video is a live Rubber Duck Thursday where the host dives into the change log, demos the new rubber duck critique fe
You Need To Change How You Use Your Claude Code Sessions
The video showcases Claude code’s versatility beyond programming, highlighting how its agent system and workflows can po
Going beyond CRUD with AI - This project has consumed me
The video documents the creation and demonstration of Fusion Q, a real-time pool training and projection system, coverin
It’s Broken… The Claude Code Vs Codex Debate Is Finally Over
The video pits Opus 4.7 against GPT 5.5 across usability, planning, building, debugging, memory, and agent capabilities
Claude Design Is Actually A Trap
The video argues that Claude Design is overhyped and that Claude Code offers more practical and capable design workflows
GPT 5.5 Arrives, DeepSeek V4 Drops, and the Compute War Intensifies
The video surveys the AI landscape through new models like GPT-5.5 and DeepSeek V4, comparing their performance, costs,