PREMIUM

Sep 6, 2026 • 6 min video

GPT-6-Astra in ChatGPT App: Browser Use and Light Level

6-minute video for Premium members. A quick test how the new GPT-6-Astra performs in Codex/ChatGPT app: how expensive is the Browser Use, and is it worth switching to Light level for saving money?

PREMIUM

Aug 29, 2026 • 7 min video

Sol vs Opus: Which One Reviews Code Better?

7-minute video for Premium members. I tested Sol vs Opus as code REVIEWERS, running the same prompt 8 times: 4 on Opus, 4 on Sol, also on different thinking levels of Medium/High. Is there a clear winner?

PREMIUM

Aug 24, 2026 • 7 min video

I Tested 5 Strong LLMs on Long-Running Prompts

7-minute video for Premium members. Experiment: what if I benchmark models not on ONE prompt, but on the set of FOUR prompts? I tried this approach with 5 top LLMs, which scored the best?

PREMIUM

Aug 17, 2026 • 12 min video

Save Money: GPT-5.6-Luna with Sol Review (Experiment)

12-minute video for Premium members. Luna is much cheaper than Sol, so can we save money/time to prepare the plan with Sol, give implementation to Luna, and then review with Sol again? Let me show you the numbers from my experiment.

PREMIUM

Aug 10, 2026 • 6 min video

I Tried Using Deepseek-v4-Flash in Codex CLI vs OpenCode

6-minute video for Premium members. I decided to test whether harness can change the results - so is DeepSeek v4 Flash in Codex CLI better/worse in terms of quality/price/speed than in OpenCode?

PREMIUM

Jul 22, 2026 • 8 min video

I Tested Kimi K3 vs Fable / Sol / Opus on 3 Coding Projects

8-minute video for Premium members. I added Kimi K3 to the previously-executed benchmark, where frontier LLMs had to fix 3 complex bugs in big open-source projects.

PREMIUM

Jul 17, 2026 • 16 min video

Frontier LLM Benchmark: Fable vs Sol vs Opus - on 3 Projects

16-minute video for Premium members. I gave the frontier models the tasks to not generate new code, but to fix existing code in the very old open-source projects, fixing real issues reported by their users.

PREMIUM

Jul 16, 2026 • 1 min read

I Tried "Destructive Command Guard" Tool. VERY Good.

11-minute video for Premium members. If you want to protect from AI agent running "rm -rf" or "drop table" as a part of the prompt, this tool will help you.

PREMIUM

Jun 30, 2026 • 1 min read

I Tried Ponytail Skill: Shorter/Better/Cheaper Code?

17-minute video for Premium members. I tested Ponytail skill in Claude Code on three different projects and prompts, comparing the speed, token usage, and the code quality.

PREMIUM

May 27, 2026 • 1 min read

I Tried /grill-with-docs Skill: Massive Difference

26-minute video for Premium members. I went through /grill-with-docs session based on a project description from a client, and then gave the result docs to Composer 2.5 to implement the code.