This Week in AI Coding: Composer 2.5, Claude Prices, and AI "Tricks"
Another weekly AI coding newsletter I've compiled with AI coding tutorials, news, and "tricks" from the community. Enjoy!
Latest Articles
Fresh insights on AI-powered development
LLM Coding Leaderboard: June 24th (16 Models Tested)
I've compiled all my recent tests with 16 different LLMs into one summary table. The results are based on 5 different Laravel projects that I published on my YouTube channel over last weeks.
PREMIUM
Codex App: 8 Features You May Not Know
11-minute video for Premium members. Codex App is really convenient to work with multiple projects at the same time. I've found quite a few "hidden tricks" that are not visible right away. Let me show you.
This Week in AI Coding: Chinese LLMs, Grok 4.3, and Free Deepseek
Another week in AI coding, and another benchmark I've performed, comparing 6 Chinese models vs frontier Western models, and added Grok 4.3 on top. In addition, new releases from AI companies and tips/tricks/tools from Twitter. Enjoy!
PREMIUM
6 Chinese LLMs: Coding Test on TWO Laravel Tasks
11-minute video for Premium members. I have given two tasks to 6 different LLMs - Kimi, MiMo, Deepseek, GLM, Qwen, and Minimax. Is there a clear winner?
This Week in AI Coding: Codex/Claude Code Tips and Tricks, and Tests with GPT-5.x
Another Wednesday with my newsletter, and I decided to make a shift. Sharing less industry news (hype) and less people screaming how "they take away our tokens" and "why it's getting slower / more expensive", and sharing more PRACTICAL ADVICE. So yeah, you'll see many tweets with just people sharing how to use AI better for coding. Enjoy!
PREMIUM
Codex CLI: My Favorite 10 Tips and Tricks
Many people are switching to Codex from Claude Code in April/May, so I thought to compile some features of Codex CLI that you may not know.
This Week in AI Coding: GPT-5.5, Deepseek v4, and "Jumping" AI Prices
Another week where AI coding community is talking more about pricing and usage than tools or LLMs. Apparently, models became all "good enough", and now everyone is trying to find their way to get maximum from their payment plan. Also, some companies are raising prices, while others reset limits and extend cheaper usage. Wild times.
PREMIUM
I Tested NEW GPT-5.5 vs GPT-5.4 vs Opus 4.7 on THREE Coding Tasks
20-minute video for Premium members. I gave three tasks to three models: to fix a bug, to plan a project, and to implement the part of the plan. I will compare the code quality, speed, and usage of the tokens.
This Week in AI Coding: Bad Opus 4.7, Good Kimi K2.6, and Growing Codex
Another week in AI Coding world, and the main topic on social media are rants on Anthropic. How bad is Opus 4.7, how ridiculous is the token usage, how they don't clearly communicate pricing changes, etc. Meanwhile, OpenAI is having a blast with growing Codex, and Chinese models like Kimi are catching up really fast.
