newsfilter.io

Boris Cherny

Showing 13 of 3 transcripts.

  1. Y Combinator36 min

    Boris Cherny: We Cut 80% of Claude Code’s Prompt

    Boris Cherny, Diana Hu

    The Opus 5 model release demonstrates a 30% score on the ARC AGI benchmark and unprecedented autonomous endurance by eliminating over 80% of legacy system prompts through an empirical ablation methodology. This shift enabled dynamic workflows where thousands of agents autonomously rewrote complex software stacks like the Bunn runtime and Cloud Code desktop app in mere days. Strategic advice for developers emphasizes replacing rigid prompt engineering with context design and verification protocols to leverage these emergent agentic capabilities effectively.

  2. Y Combinator1 min

    What Boris Cherny Learned From Building Claude Code

    Boris Cherny

    Quad Code's founder executed a grueling three-month sprint to launch a terminal-based product, accepting current code-generation limitations as an inevitable starting point rather than a final state. This strategy mirrors Anthropic's philosophy of building software for capabilities expected six months into the future, encouraging founders to target where models currently fail rather than optimizing for today's constraints. By prioritizing this forward-looking approach, both entities anticipate that natural model progression will resolve existing gaps without requiring premature adaptation to immature technology.

  3. Y Combinator50 min

    Inside Claude Code With Its Creator Boris Cherny

    Boris Cherny, Mark Mandelmann, Jr., Francesc Campoy, Melanie Warrick

    Anthropic has accelerated its engineering velocity to a 150% growth rate by leveraging *Claude Code* to generate 70% to 90% of its own source code and rewriting its entire codebase every six months to avoid technical debt. The organization operates a bimodal workforce of specialists and generalists while predicting that traditional software engineering roles will fade as AI automates coding tasks. With *Claude Code* now powering the majority of developer sessions and influencing 4% of public industry commits, the company is simultaneously expanding into non-technical domains through *Co-work* and monitoring its safety rating at ASL 3.