💥 After years in the C-suite, I reopened VS Code and built an AI-native product—solo.
Here’s what a few gritty weeks shipping code with AI teammates taught me. 👇
If the same system that wrote the change also picks who reviews it, the review is theater.
Generation got cheap. Judgment didn't. Most teams feed the output back into the same loop that produced it.
A decision only counts if the procedure sits outside the thing being judged.
Good to see a response from @AnthropicAI but too late and not enough. Fable and Opus have become unusable for serious at-speed agentic development. We have moved all primary code gen activities to Grok Build 4.6. Incredibly fast, concise, great decision making and objective oriented.
You can now set Claude Code's output style to Concise.
Claude leads with the result, keeps responses short, and still gives full detail when you ask.
Turn it on in /config → Output style, or set "outputStyle": "Concise" in settings.json.
New in Claude Code: your sessions can now message each other.
Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.
Kimi-K3 just topped the Frontend Code Arena with a 76% pairwise win rate.
When its output was compared head-to-head against other models on the same task, it was picked as the better output 76% of the time on average.
For reference: Claude Fable 5 (63%), GPT-5.6 Sol (58%). 50% is baseline, a model winning and losing equally often.
Just saw play in Texans vs Patriots. Houston receiver catches ball, doesn’t make a football move, on way to ground knee hits, right afterwards Pats defender rips ball out. They call it down by contact. Exact same scenario but this time down by contact. This logic that it’s an interception just doesn’t hold. He’s down by contact.
If a player is contacted by another player in possession of the ball and on the ground (knees, etc) the play is dead. If we open that interpretation up to the ability for other players to rip the ball out while they are on the ground then we’ll get defenses now basically spearing players again while on the ground to jar the ball loose or rip it out to turn the catch into a no catch. It would be different if the ball was not in control before the defender contacted him on the ground. But he was clearly in control of the ball, in contact with the ground and the defender ripped it out. So evidently that continuation rule is taking precedent but logically it just seems backward and against the spirit of the rules.