UPDATED JUNE 28, 2026
UPDATED JUNE 28, 2026

The Frontier

Your signal. Your price.

Include
Lookback
||
  • · 7d ago

    Boris Cherny states that 100% of his code is written by Claude Code, with no manual edits since November 2024. He ships 10-30 pull requests daily and often runs five agents simultaneously.

  • · 7d ago

    Cherny advocates underfunding projects initially to force teams to 'Claudify' and automate work with AI. He advises leaders to give engineers unlimited tokens for experimentation, then optimize costs only after an idea proves successful.

  • · 7d ago

    Cherny advises builders to design for the AI model six months from now, not its current capabilities. He warns against over-engineering workflows, arguing the more general model will always outperform a specialized, scaffolded one.

  • · 7d ago

    For using Claude Code, Cherny recommends always using the most capable model, starting tasks in 'plan mode', and experimenting with different interfaces beyond the terminal.

  • · 7d ago

    Cherny describes a three-layer safety approach at Anthropic: mechanistic interpretability to study model neurons, laboratory evals, and studying model behavior in the wild through early product releases.

  • · 7w ago

    Claude Code creator Boris Cherny disavowed the term 'vibe coding', stating his company uses coordinated AI agents over Slack with automated testing and no manually written code.

  • · 2mo ago

    Albert and Boris propose interactive branded games as a new advertising format, suggesting a brand like Domino's could create an asteroid-style game to directly drive pizza orders.

End of 90-day results — 7 results
7 results